Skip to content

Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.

docs(parity): add the awesome-solana-ai submission kit and trim orders 919 to 921 to their owner-gated steps

nirholas0e0a806cdc16
diff --git a/docs/awesome-solana-ai-submission.md b/docs/awesome-solana-ai-submission.md
new file mode 100644
index 000000000..e4b7a890f
--- /dev/null
+++ b/docs/awesome-solana-ai-submission.md
@@ -0,0 +1,93 @@
+# awesome-solana-ai submission
+
+Target: `solana-foundation/awesome-solana-ai` (README.md, ~428 stars, community list maintained under the Solana Foundation GitHub organization).
+
+Checked against production and the list on 2026-10-23.
+
+## State
+
+- PR #251, "Add three.ws to AI Agents", is open (not merged, 1 comment, no review feedback, mergeable). It adds one line under **AI Agents** pointing at the repository.
+- three.ws is not yet in the README, and it has no entry under **AI Coding Skills > General**, where `https://three.ws/skill.md` belongs. That entry is the new submission this doc prepares. It should go in as a second, separate PR so the agents entry and the skill entry can be reviewed independently.
+
+## Rules from CONTRIBUTING.md
+
+- Related to AI and Solana development; format `[name](link) - Brief description.`; one concise sentence; correct spelling.
+- Actively maintained, documented, working code usable today.
+- Not a token promotion, not a paid promotion, not vaporware. The line below therefore describes developer capability and does not mention a coin.
+- PR process: fork, branch, change README.md only, clear description.
+
+## The line (primary): AI Coding Skills > General
+
+The section is alphabetical by name; `three-ws-skill` sorts after the current last entry, so it is appended at the end of **General**.
+
+```diff
+--- a/README.md
++++ b/README.md
+@@ General @@
++- [three-ws-skill](https://three.ws/skill.md) - AI agent skill for three.ws: generate textured and rigged 3D models and avatars, create agents with their own Solana wallet, and pay for or sell services over x402.
+```
+
+The draft in the work order also said "launch coins". It is dropped on purpose: the list rejects projects "primarily designed to promote or shill a token", and the skill is a developer capability set, so the line stays about tooling.
+
+## The line (secondary): Developer Tools (hosted MCP)
+
+Developer Tools is not alphabetical, so the entry is appended after the last MCP-server item.
+
+```diff
++- [three.ws MCP](https://three.ws/connect) - Hosted MCP servers for AI clients: free text-to-3D and avatar rigging with no account, plus agent wallets, memory and x402 payments on Solana, with one-click setup for Claude, ChatGPT, Cursor and VS Code.
+```
+
+Primary is the skill line (it is our `skill.md` entry point). The MCP line is optional and can be sent in the same PR.
+
+## Claims re-checked against production on 2026-10-23
+
+| Claim | Check | Result |
+|---|---|---|
+| `https://three.ws/skill.md` is live | `curl -I` | 200, `text/markdown` |
+| `https://three.ws/connect` is live | `curl -I` | 200 |
+| Free 3D generation with no account | `POST /api/mcp-studio` `tools/list` with no auth | returns `forge_free` and the rest of the toolset |
+| Hosted MCP directory | `GET /.well-known/mcp.json` | 200 |
+| Agents with a Solana wallet, x402 | `skill.md` documents both (7 matches for wallet, launch or x402) and the platform ships them | true |
+| Rigged avatars | `forge_avatar` and `rig_mesh` in the same `tools/list` | true |
+
+## Branch, commit, PR
+
+Run from an account with GitHub auth. `gh` is not installed on the build machine, so these are plain git plus the web or `gh` flow.
+
+```bash
+gh repo fork solana-foundation/awesome-solana-ai --clone && cd awesome-solana-ai
+git switch -c add-three-ws-skill
+# append the line under "### General" (after the last list item, before "### DeFi")
+git commit -am "Add three-ws-skill to AI Coding Skills > General"
+git push -u origin add-three-ws-skill
+gh pr create --title "Add three-ws-skill to AI Coding Skills > General" --body-file pr-body.md
+```
+
+### PR title
+
+Add three-ws-skill to AI Coding Skills > General
+
+### PR body
+
+three.ws is an open-source platform that gives AI agents a body: generated 3D models and rigged avatars, a public page, a Solana wallet per agent, and per-call x402 payments settled on Solana. Its agent entry point is a single skill file.
+
+Why it fits: `https://three.ws/skill.md` is a working agent skill (MIT, maintained, public repo) that tells an agent how to connect over MCP, generate and rig 3D assets for free, create an agent with its own Solana wallet, and pay for or sell services over x402. It contains no token promotion.
+
+Links: skill https://three.ws/skill.md, MCP setup https://three.ws/connect, source https://github.com/nirholas/three.ws. This is a separate PR from #251, which adds the repository under AI Agents.
+
+## Other directories where three.ws is missing
+
+Source of truth: [listings-registry.md](./listings-registry.md) (`npm run listings:verify` re-checks it).
+
+| Directory | State | Exact step |
+|---|---|---|
+| mcp.so | Not listed (search returned 0 on 2026-10-11) | Sign in at https://mcp.so, "Submit", paste `https://github.com/nirholas/three.ws` and the endpoint `https://three.ws/api/mcp`. |
+| Smithery | Not listed | `npx @smithery/cli publish` from a server directory with a `smithery.yaml`, or submit the remote URL `https://three.ws/api/mcp-studio` at https://smithery.ai/new. |
+| LobeHub chat plugin index | Not listed (`/.well-known/lobehub-plugin.json` exists) | Open a PR adding the manifest URL to the LobeHub plugin index repository per its README. |
+| Solana Foundation pay-skills | PR #302 open | Chase the maintainer; nothing to resubmit. |
+
+All of these are posting to an external channel and are owner-gated.
+
+## Owner message (one yes)
+
+Submit two things: (1) new PR to `solana-foundation/awesome-solana-ai` with the `three-ws-skill` line above (and optionally the MCP line), title and body as written; (2) mcp.so and Smithery submissions as listed. PR #251 stays as is. Reply yes and the commands above run from an authenticated GitHub account.
diff --git a/prompts/finish/919-parity-09-ship-and-publish.md b/prompts/finish/919-parity-09-ship-and-publish.md
index 15ed37e7e..3095f09f9 100644
--- a/prompts/finish/919-parity-09-ship-and-publish.md
+++ b/prompts/finish/919-parity-09-ship-and-publish.md
@@ -1,63 +1,12 @@
-# parity 09: push, deploy, and publish the three-ws CLI
+# parity 09: remaining owner steps for the three-ws CLI
-How to run: paste this file's repo path into a fresh Claude Code chat in this repository and say "run this work order". Band 900: the last steps are owner actions (push, production deploy, npm publish). Everything before them is yours.
+Trimmed 2026-10-23. Built and committed: the unscoped `three-ws` launcher package in `packages/three-ws/` (pins `@three-ws/[email protected]`, 4 tests passing). What remains is owner-gated (CLAUDE.md gate 2: push, deploy, publish).
-## Operating clause (binding)
+## Remaining
-- Read CLAUDE.md first, then [_context/parity-00-CONTEXT.md](_context/parity-00-CONTEXT.md). CLAUDE.md overrides everything, including this file.
-- Finish 100% in this session. Never end the turn with a question, an option list, or an unexecuted plan. A judgment call goes in one line of the final report; it never becomes a question that halts work.
-- The only permitted stops are the CLAUDE.md stop-and-ask gates: spending real funds or any irreversible on-chain write, git push or a production deploy, committing content that names a crypto project other than $THREE, and destroying unrecoverable data. Where this order hits one, it says so, and you batch every such ask into ONE message after everything else is done.
-- Never name Competitor X in anything you commit. If a reference is unavoidable, write "Competitor X".
-- No mocks, no fake data, no placeholder stubs, no unfinished-work markers, no commented-out code. Real APIs and real integrations only.
-- The em-dash and en-dash characters are banned in everything you write.
-- Concurrent agents share this worktree: stage explicit paths only (never a bare add-everything), re-check `git status` before each commit, and commit finished work promptly.
-- Before committing, run `npm run check:rules -- --paths <files you touched>`. It must exit 0.
+1. `git push threews main` (owner approval).
+2. Deploy per the `deploy-runbook` skill (`npm run deploy:gcp:full`).
+3. `cd packages/three-ws && npm login && npm publish --access public`. The first publish of a new name sits behind a 0.0.0-stage hold for a few minutes; wait for it to clear.
+4. Verify: `npx three-ws --version` prints 0.1.1, then `npm run smoke:prod`.
-## Why this matters
-
-Every hosted MCP server answers an unauthenticated call with a 401 whose body says `Run npx three-ws setup` and links `https://three.ws/docs/cli`, and `/.well-known/mcp.json` advertises the same command. On 2026-09-29 the `three-ws` package had never been published (`npm view three-ws` returned E404), so that command failed for every developer who tried it. The Tier 1 work (`/connect`, `/docs/cli`, `/skill.md`, the curated `llms.txt`, the footer notice, the CLI's `create` and `launch`) is committed on `main` but was not live.
-
-## Step 0: re-derive the current state
-
- git fetch threews main && git log --oneline threews/main..main | wc -l
- curl -s https://three.ws/api/version
- for p in /connect /docs/cli /skill.md /llms.txt; do printf "%s " $p; curl -s -o /dev/null -w "%{http_code} %{content_type}\n" https://three.ws$p; done
- (cd /tmp && npm view three-ws version 2>&1 | head -1)
- npm whoami 2>&1 | head -1
- npx vitest run packages/three-ws-cli/tests
-
-Record each result. Skip any task below whose outcome step 0 shows is already true.
-
-## Tasks
-
-1. **Make the package publish-ready.** In `packages/three-ws-cli`: run `npm pack --dry-run` and confirm the tarball holds `src/`, `README.md` and `LICENSE` and nothing else (no tests, no `node_modules`). Confirm `bin`, `engines`, `publishConfig.access: public` and the dependency ranges in `package.json`. Run the CLI from the packed tarball in a clean temp dir (`npm pack`, then `npx --yes ./three-ws-<version>.tgz version` and `... mcp list --available`) and confirm both work against production. Fix anything that fails at root and commit it.
-2. **Prepare the deploy exactly as the CLAUDE.md Deploy runbook says**, in order: `npm run clean:worktrees`, `npm run prep:worktree` (plan) then `-- --apply`, `npm run build:gcp` inside the worktree, and run the `deploy-preflight` subagent against it. Stop before `npm run deploy:gcp:submit`.
-3. **Send the ONE owner message** (the gate). It asks for three yeses, each with what it does: (a) `git push threews main`, listing the commit count from step 0; (b) the production deploy from the prepared worktree; (c) `npm publish` of `three-ws@<version>` from `packages/three-ws-cli`, which needs an npm account with publish rights (if `npm whoami` failed, ask for `npm login` in the same message). If the owner's current instruction already approves any of these (for example "ship it"), that is the approval: do not ask again.
-4. **After approval**, run the approved steps: the push, then `npm run deploy:gcp:submit`, `npm run deploy:gcp:purge-cdn`, then `npm publish` from the package directory. Remove the deploy worktree when it lands (`git worktree remove --force <path>`).
-5. **Verify live**, every line against production: `curl -s https://three.ws/api/version` shows the pushed commit; `/connect` and `/docs/cli` return 200 and render (Playwright, no console errors); `/skill.md` returns 200 with `text/markdown`; `/llms.txt` starts with the `## Official` block within its first 20 lines; `npm run smoke:prod` passes; and from an empty temp directory `npx --yes three-ws@latest version` prints the published version and `npx --yes three-ws mcp list --available` lists the hosted servers.
-
-## Definition of done
-
-- [ ] `git log --oneline threews/main..main` is empty for the commits that existed at step 0.
-- [ ] `curl -s https://three.ws/api/version` reports a commit at or after the pushed head.
-- [ ] `/connect`, `/docs/cli`, `/skill.md` and `/llms.txt` return 200 on production, `/skill.md` as `text/markdown`.
-- [ ] `npm view three-ws version` prints a version; `npx --yes three-ws@latest mcp list --available` works in an empty directory.
-- [ ] `npm run smoke:prod` exits 0.
-
-## Never blocked
-
-| Blocker | Resolution (act, do not ask) |
-|---|---|
-| `gcloud` answers `Reauthentication failed` | Retry one real call; if it persists, it goes into the single owner message as `gcloud auth login`, alongside the three approvals. Everything up to the submit is still yours. |
-| `npm whoami` fails | Same: `npm login` joins the single owner message. Finish the publish-readiness task regardless. |
-| Migrations pending at `db:check` | `npm run db:status`, then `npm run db:migrate` (it applies every pending migration; read the status first). |
-| A build step fails in code you did not touch | Root-cause and fix it if it blocks the build; the CLAUDE.md runbook lists the known failure modes. |
-| The npm name is taken at publish time | Stop the publish, report it, and do not rename the package: every 401, `/docs/cli` and `/.well-known/mcp.json` name `three-ws`. |
-| Production smoke fails on a page unrelated to this order | Report it as a named follow-up; it does not block this order unless it is one of the four surfaces above. |
-
-## Close out (required)
-
-1. Verify every Definition of done line with the actual command output in front of you. Never claim a line you did not verify.
-2. Commit with explicit paths and a subject that describes the diff (house style: `type(scope): what changed and why a reader cares`).
-3. If every Definition of done line passes, delete this file in that same commit (`git rm prompts/finish/919-parity-09-ship-and-publish.md`) and append a dated entry to [_context/parity-PROGRESS.md](_context/parity-PROGRESS.md) with the commit SHAs. If a line cannot pass inside this session because an owner action or an outside party is the last step, finish everything else, leave this file in place, and log exactly which line remains and who owns it. Never delete this file on a partial.
-4. Final report, in this order: what step 0 measured; what changed (file list with commit SHAs); evidence for each Definition of done line; the single batched owner message, if the order has a gate; one-line judgment calls. No trailing questions.
+Close out: when 1 to 4 pass, `git rm` this file in its own commit and log it in `_context/parity-PROGRESS.md`.
diff --git a/prompts/finish/920-parity-10-community-skill-registry.md b/prompts/finish/920-parity-10-community-skill-registry.md
index d2c8615c8..ba9bdd097 100644
--- a/prompts/finish/920-parity-10-community-skill-registry.md
+++ b/prompts/finish/920-parity-10-community-skill-registry.md
@@ -1,64 +1,11 @@
-# parity 10: pull community skills from external GitHub registries
+# parity 10: remaining owner step for external community skills
-How to run: paste this file's repo path into a fresh Claude Code chat in this repository and say "run this work order". Band 900: the owner chooses which external registries to trust. Build everything else first.
+Trimmed 2026-10-23. Built and committed in `dd69b9b4b`: operator-pinned external GitHub skill sources (`api/_lib/community-skill-sources.js`), the API, the CLI import path, and the labelled section on /skills-community. Never auto-enabled; installs go through the existing scan and approval flow. Tests and a browser pass are green.
-## Operating clause (binding)
+## Remaining (owner)
-- Read CLAUDE.md first, then [_context/parity-00-CONTEXT.md](_context/parity-00-CONTEXT.md). CLAUDE.md overrides everything, including this file.
-- Finish 100% in this session. Never end the turn with a question, an option list, or an unexecuted plan. A judgment call goes in one line of the final report; it never becomes a question that halts work.
-- The only permitted stops are the CLAUDE.md stop-and-ask gates: spending real funds or any irreversible on-chain write, git push or a production deploy, committing content that names a crypto project other than $THREE, and destroying unrecoverable data. Where this order hits one, it says so, and you batch every such ask into ONE message after everything else is done.
-- Never name Competitor X in anything you commit. If a reference is unavoidable, write "Competitor X".
-- No mocks, no fake data, no placeholder stubs, no unfinished-work markers, no commented-out code. Real APIs and real integrations only.
-- The em-dash and en-dash characters are banned in everything you write.
-- Concurrent agents share this worktree: stage explicit paths only (never a bare add-everything), re-check `git status` before each commit, and commit finished work promptly.
-- Before committing, run `npm run check:rules -- --paths <files you touched>`. It must exit 0.
+1. Approve the source list (each entry is `{repo, ref, path, license}` with `ref` a 40-hex commit sha and a permissive license). The proposed list is in the session report.
+2. Set it on Cloud Run with `gcloud run services update three-ws-api --region us-central1 --update-env-vars COMMUNITY_SKILL_SOURCES='[...]'` (never `--set-env-vars`).
+3. Verify `GET /api/skills/community` returns an `external` object, then add the changelog entry and run `npm run build:pages`.
-## Why this matters
-
-Competitor X lists about 50 "community skills" by pulling two public GitHub skill repositories at runtime (one of them a widely used Apache-2.0 library of 44 Solana protocol skills) and caching them for five minutes. Our registry is richer in validation but closed: every skill must be committed to `community-skills/` in this repo (or merged through the mirror, `scripts/sync-community-skills.mjs`). Pulling vetted external registries widens the catalog without us writing or hosting each skill.
-
-The risk is real and is the design constraint: a skill is a set of instructions an agent loads. An external skill is untrusted input. It must never be auto-enabled, must be pinned to a commit, and must be labelled as external everywhere it appears.
-
-## Step 0: re-derive the current state
-
- sed -n 1,60p api/_lib/community-skills.js
- sed -n 1,40p api/skills/community.js
- python3 -c "import json;d=json.load(open('community-skills/registry.json'));print(d['count'], d['schema'], list(d)[:8])"
- sed -n 1,60p packages/three-ws-cli/src/commands/skills.js
- grep -rn "COMMUNITY_SKILL_SOURCES" api scripts packages 2>/dev/null
- node scripts/read-service-env.mjs '^COMMUNITY_SKILL_SOURCES$' --raw
-
-Note the registry schema (`community-skills/registry.json`), how `/skills/community` and `GET /api/skills/community/:slug` read it, how `three-ws skills import` installs one, and whether any external-source code already exists.
-
-## Tasks
-
-1. **Source list from runtime config, not code.** Read the list of external registries from one env var, `COMMUNITY_SKILL_SOURCES`: a JSON array of `{ "repo": "owner/name", "ref": "<commit sha>", "path": "skills", "license": "<SPDX id>" }`. Nothing in committed code, tests or docs names a specific third-party repository (the commit gate); tests use a synthetic repository fixture served by a local HTTP server.
-2. **Fetch, validate, cache.** A server module (beside `api/_lib/community-skills.js`) fetches each source's skill folders at the pinned `ref` from `raw.githubusercontent.com` (tree listing through the public GitHub API, unauthenticated, with `GITHUB_TOKEN` used when set to lift the rate limit), validates every `SKILL.md` with the same frontmatter rules as our registry, drops anything invalid with a logged reason, and caches the merged result (memory plus a short TTL). A source that fails to load never breaks our own registry: our in-image skills always render.
-3. **Label and isolate.** Every external skill carries `origin: "external"`, its source repo, the pinned commit, and its license in the API response. `/skills/community` shows them in their own clearly labelled section with a "not reviewed by three.ws" badge and a link to the exact source commit. They can be imported only by an explicit user action; nothing enables them on any agent automatically; `three-ws skills import` prints the source and commit and asks for confirmation (non-interactive use requires `--yes`).
-4. **Docs.** Extend `community-skills/README.md` (or the doc it links) with how external sources work, the trust model and how an operator adds one (the env var format). Add a `data/changelog.json` entry once live.
-5. **The owner message (the gate).** Propose a concrete source list: for each candidate, the repository, a pinned commit, its license, its skill count and why it is worth including. Candidates must be permissively licensed (MIT, Apache-2.0, BSD). Ask for a yes on the list, then set the approved value with `gcloud run services update three-ws-api --region us-central1 --update-env-vars` (config-only updates are pre-approved once the list is approved; never `--set-env-vars`).
-
-## Definition of done
-
-- [ ] With `COMMUNITY_SKILL_SOURCES` unset, `/skills/community` and its API behave exactly as before (a test proves it).
-- [ ] With the synthetic fixture source set, the API returns the fixture's valid skills with `origin: "external"`, `source`, `ref` and `license`, and omits the invalid one (a test proves each).
-- [ ] A failing source (404, timeout) leaves the in-repo registry intact and is logged (a test proves it).
-- [ ] `three-ws skills import` of an external skill without `--yes` in a non-interactive shell refuses (a test proves it).
-- [ ] `grep -rn` over the diff finds no third-party repository name.
-- [ ] `npm test` passes for the touched suites; `npm run check:rules -- --paths <files>` exits 0.
-- [ ] The owner message with the proposed source list was sent (quote it in the report). Setting the env var is the only step allowed to remain.
-
-## Never blocked
-
-| Blocker | Resolution (act, do not ask) |
-|---|---|
-| GitHub API rate limit (60/hour unauthenticated) | Use `GITHUB_TOKEN` when present (check `.env`, `.env.local`, the service env); otherwise rely on the cache and fetch by pinned tree once per TTL. |
-| An external `SKILL.md` has non-standard frontmatter | Drop it with a logged reason; never loosen our validator to admit it. |
-| A candidate repository has no license | Exclude it from the proposal and say why. |
-
-## Close out (required)
-
-1. Verify every Definition of done line with the actual command output in front of you. Never claim a line you did not verify.
-2. Commit with explicit paths and a subject that describes the diff (house style: `type(scope): what changed and why a reader cares`).
-3. If every Definition of done line passes, delete this file in that same commit (`git rm prompts/finish/920-parity-10-community-skill-registry.md`) and append a dated entry to [_context/parity-PROGRESS.md](_context/parity-PROGRESS.md) with the commit SHAs. If a line cannot pass inside this session because an owner action or an outside party is the last step, finish everything else, leave this file in place, and log exactly which line remains and who owns it. Never delete this file on a partial.
-4. Final report, in this order: what step 0 measured; what changed (file list with commit SHAs); evidence for each Definition of done line; the single batched owner message, if the order has a gate; one-line judgment calls. No trailing questions.
+Close out: when done, `git rm` this file in its own commit.
diff --git a/prompts/finish/921-parity-11-directory-listings.md b/prompts/finish/921-parity-11-directory-listings.md
index d4315a9f7..e6ef4138d 100644
--- a/prompts/finish/921-parity-11-directory-listings.md
+++ b/prompts/finish/921-parity-11-directory-listings.md
@@ -1,57 +1,9 @@
-# parity 11: list three.ws in the directories agents and builders read
+# parity 11: remaining owner step for directory listings
-How to run: paste this file's repo path into a fresh Claude Code chat in this repository and say "run this work order". Band 900: opening a pull request on someone else's repository is posting to an external channel, so the submission itself is owner-gated. Everything up to it is yours.
+Trimmed 2026-10-23. Prepared and committed: `docs/awesome-solana-ai-submission.md` (exact README line, PR title and body, production claim checks, steps for mcp.so and Smithery). PR #251 (AI Agents entry) is already open and unmerged.
-## Operating clause (binding)
+## Remaining (owner)
-- Read CLAUDE.md first, then [_context/parity-00-CONTEXT.md](_context/parity-00-CONTEXT.md). CLAUDE.md overrides everything, including this file.
-- Finish 100% in this session. Never end the turn with a question, an option list, or an unexecuted plan. A judgment call goes in one line of the final report; it never becomes a question that halts work.
-- The only permitted stops are the CLAUDE.md stop-and-ask gates: spending real funds or any irreversible on-chain write, git push or a production deploy, committing content that names a crypto project other than $THREE, and destroying unrecoverable data. Where this order hits one, it says so, and you batch every such ask into ONE message after everything else is done.
-- Never name Competitor X in anything you commit. If a reference is unavoidable, write "Competitor X".
-- No mocks, no fake data, no placeholder stubs, no unfinished-work markers, no commented-out code. Real APIs and real integrations only.
-- The em-dash and en-dash characters are banned in everything you write.
-- Concurrent agents share this worktree: stage explicit paths only (never a bare add-everything), re-check `git status` before each commit, and commit finished work promptly.
-- Before committing, run `npm run check:rules -- --paths <files you touched>`. It must exit 0.
+Say yes to the batched submission in the doc: a second PR to `solana-foundation/awesome-solana-ai` adding the `three-ws-skill` line under AI Coding Skills > General, plus the mcp.so and Smithery submissions. `gh` is not installed or authenticated on the build machine, so the commands in the doc run from an authenticated account.
-## Why this matters
-
-The Solana Foundation's `solana-foundation/awesome-solana-ai` README (about 426 stars on 2026-09-29, pushed weekly) is a curated list of AI coding skills, agents and tools for Solana. Competitor X is listed there twice and cites the listing as credibility on its own marketing page. three.ws is not listed. Our entry point for an agent is `https://three.ws/skill.md` (shipped 2026-09-29, order 919 makes it live).
-
-## Step 0: re-derive the current state
-
- curl -s -o /dev/null -w "%{http_code} %{content_type}\n" https://three.ws/skill.md
- curl -s https://raw.githubusercontent.com/solana-foundation/awesome-solana-ai/main/README.md | grep -n "^#\|three.ws\|three-ws"
- curl -s https://raw.githubusercontent.com/solana-foundation/awesome-solana-ai/main/CONTRIBUTING.md
- which gh; gh auth status 2>&1 | head -3
-
-If `/skill.md` is not 200 on production, order 919 has not landed: finish the preparation below and log that the submission waits on 919.
-
-## Tasks
-
-1. Read the list's CONTRIBUTING rules and match them exactly: section, alphabetical position, line format, description length.
-2. Decide the section from its content: `https://three.ws/skill.md` belongs under **AI Coding Skills > General**; if the list has an **AI Agents** or **Developer Tools** entry that fits the hosted MCP servers (`https://three.ws/connect`), prepare that second line too, and say which is primary.
-3. Write the lines. Draft for the skill: `[three-ws-skill](https://three.ws/skill.md) - AI agent skill for three.ws: generate textured and rigged 3D models and avatars, create agents with their own Solana wallet, launch coins, and pay for or sell services over x402.` Every claim must be true on production the day you submit; re-check each one.
-4. Prepare the pull request in a local clone under the session scratchpad: branch, the one-file README diff, a commit and a PR title and body written for the list's maintainers (what three.ws is in two sentences, why it fits the list, links to `/skill.md`, `/connect` and the repo). Save the diff, title and body to `docs/awesome-solana-ai-submission.md` in this repo and commit it.
-5. Look for other directories of the same kind (Agent Skills registries, MCP server directories we are not yet in; `STRUCTURE.md` and `docs/` list the ones we are). For each one missing us, add its exact submission steps to the same doc.
-6. **The owner message (the gate):** the list of submissions, each with its target, the exact text and the PR body, asking for one yes. On a yes, submit with `gh` from an authenticated account (install `gh` if missing), or hand the owner the one command if the machine has no GitHub auth.
-
-## Definition of done
-
-- [ ] `docs/awesome-solana-ai-submission.md` holds the exact diff, PR title and body, plus any other directory's steps, and is committed.
-- [ ] Every claim in the proposed lines was re-checked against production that day (the report lists each check).
-- [ ] The owner message was sent. The submission itself is the only step allowed to remain, and the report names the PR URL if it was opened.
-
-## Never blocked
-
-| Blocker | Resolution (act, do not ask) |
-|---|---|
-| `gh` not installed or not authenticated | Prepare everything; the submission command goes in the owner message. |
-| The list's rules forbid self-submission | Say so in the owner message and prepare the text for a third party to submit. |
-| `/skill.md` not live yet | Prepare everything and log that the submission waits on order 919. |
-
-## Close out (required)
-
-1. Verify every Definition of done line with the actual command output in front of you. Never claim a line you did not verify.
-2. Commit with explicit paths and a subject that describes the diff (house style: `type(scope): what changed and why a reader cares`).
-3. If every Definition of done line passes, delete this file in that same commit (`git rm prompts/finish/921-parity-11-directory-listings.md`) and append a dated entry to [_context/parity-PROGRESS.md](_context/parity-PROGRESS.md) with the commit SHAs. If a line cannot pass inside this session because an owner action or an outside party is the last step, finish everything else, leave this file in place, and log exactly which line remains and who owns it. Never delete this file on a partial.
-4. Final report, in this order: what step 0 measured; what changed (file list with commit SHAs); evidence for each Definition of done line; the single batched owner message, if the order has a gate; one-line judgment calls. No trailing questions.
+Close out: when the PR URL exists, `git rm` this file in its own commit.
diff --git a/prompts/finish/_context/parity-PROGRESS.md b/prompts/finish/_context/parity-PROGRESS.md
index 9b5e63c2f..a73886faa 100644
--- a/prompts/finish/_context/parity-PROGRESS.md
+++ b/prompts/finish/_context/parity-PROGRESS.md
@@ -92,3 +92,9 @@ Cross-session handoff for the `parity-` orders ([parity-00-CONTEXT.md](parity-00
- Shipped in `353a5a177`: `paidEndpoint` now records a failure after settlement (streaming handler throw, `siwx_record_failed`) as `failed_after_settle` and answers with `paid: true`, `retry_safe`, the settlement transaction, `retries_left` and a plain sentence; the same X-PAYMENT header re-runs the work with no second verify or settle (bounded by `X402_PAID_RETRY_MAX` and the retry window), a completed call still answers 409, an exhausted proof answers 409 `payment_retries_exhausted`. The helpers in `api/_lib/x402/spent-payments.js` and the migration existed from earlier commits but nothing in the wrapper called them; that wiring is the substance of this order. POST bodies now join the payment-identifier idempotency hash. `docs/mcp.md` has a Use cases section per guided prompt, guarded by `tests/mcp-use-cases-doc.test.js` (red run shown by renaming `pay_and_call()` in the doc). Docs: `docs/x402.md`, error table in `docs/api-reference.md`, changelog entry.
- Verified: 13 tests in `tests/api/x402-spent-payments.test.js` (retry, replay 409, exhausted, siwx, POST body red/green), 179 x402/MCP test files green.
- Not from this order: `npm run audit:docs` reports only `workers/cad-forge` (another lane's untracked directory) missing its README.
+
+## 2026-10-23: orders 919, 920, 921 (built, owner steps remain)
+
+- 919: `three-ws` launcher package committed in `2859eb153`; push, deploy and `npm publish` are owner-gated.
+- 920: external community skill sources committed in `dd69b9b4b`; owner approves the source list and sets `COMMUNITY_SKILL_SOURCES`.
+- 921: submission kit in `docs/awesome-solana-ai-submission.md`; PR #251 already open; second PR and mcp.so/Smithery await the owner.