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.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
chore(prompts): retire the packages-batch-11 and reputation-market work orders
nirholas60a2adcc9d44
diff --git a/prompts/swarm-100/packages-batch-11.md b/prompts/swarm-100/packages-batch-11.mddeleted file mode 100644index c9a866037..000000000--- a/prompts/swarm-100/packages-batch-11.md+++ /dev/null@@ -1,95 +0,0 @@-# Package audit batch 11: vision-mcp, voice, vscode-x402, x402-fetch, x402-mcp, x402-server--How to run: paste this file's repo path into a fresh Claude Code chat in this-repository and say "run this work order". This file is fully self-contained:-it depends on no other prompt file anywhere. If neighboring files in-prompts/swarm-100/ are gone, that work is done; if present, ignore them.-Every claim below rots; step 0 re-measures, and what you measure wins.--## Operating clause (binding)--- Read CLAUDE.md first. Its rules override 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 references a crypto project other than $THREE, and- destroying unrecoverable data.-- 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), and commit finished work promptly.-- Before committing, run: npm run check:rules -- --paths <files you touched>.- It must exit 0.--## Step 0: re-derive the current state--For each package below: read its package.json and README.md, then find its-tests (its own directory and tests/ at the repo root).--## Task: audit and fix these packages--Packages in this batch:--- packages/vision-mcp-- packages/voice-- packages/vscode-x402-- packages/x402-fetch-- packages/x402-mcp-- packages/x402-server--For each one:--1. README: present (repo standard is 100% coverage under packages/) and- accurate: what it does, install and use, public exports, one runnable- example. Run the example for real.-2. Exports resolve: import the package's declared entry points with node and- confirm they load without error.-3. Tests: run the tests that cover it; if its core path has none, add a real- one.-4. Hard-rule scan across its source: no stubs, no mock fallbacks, no- unfinished markers, no commented-out code. Fix at root.-5. package.json sanity: name, version, license, exports and files fields- consistent with what is actually shipped.--## Definition of done--- [ ] Every package in the batch: README verified accurate, example executed,- entry points imported cleanly, tests green with core-path coverage.-- [ ] Zero hard-rule violations remain in these packages.-- [ ] npm run check:rules -- --paths <touched files> exits 0.--## Never blocked--| Blocker | Resolution (act, do not ask) |-|---|---|-| Missing env var or credential | Check .env and .env.local, then the Cloud Run service env, then Secret Manager (the CLAUDE.md self-unblock playbook has the exact commands). If it truly exists nowhere, wire the code fully behind the env var, prove the wiring with a dry run, and name the single missing var in the report. |-| gcloud not on PATH | Run: export PATH="$HOME/google-cloud-sdk/bin:$PATH" |-| Dev server port 3000 busy | Another agent may be serving this repo; probe it and reuse if so. Otherwise start your own on a free port: npx vite --port 3101 |-| Playwright browser missing | npx playwright install chromium |-| A surface needs a signed-in user | Register a fresh account through the real /register flow against the real API and use it. Never mock the session. |-| A defect sits in code you did not touch | Fix it if it blocks a Definition of done line (root cause it, never mask it). Otherwise note it in the report and continue. |-| An unrelated test is red | Same rule. Never pipe npm test through tail; it masks exit codes. |--## 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. Delete this prompt file in that same commit:-- git rm prompts/swarm-100/packages-batch-11.md-- The shrinking directory is this campaign's only progress ledger; there is- no progress log to update.-4. Final report: what step 0 measured, what changed (file list), evidence per- Definition of done line, and any one-line judgment calls. No trailing- questions, no unexecuted plans.--If a line genuinely cannot pass inside this session (an external party must-respond, or an owner-gated action is the final step), finish everything else,-leave this file in place, and state exactly which line remains and who owns-it. Never delete this file on a partial.diff --git a/prompts/swarm-100/roadmap-p3-reputation-market.md b/prompts/swarm-100/roadmap-p3-reputation-market.mddeleted file mode 100644index bf8c0631e..000000000--- a/prompts/swarm-100/roadmap-p3-reputation-market.md+++ /dev/null@@ -1,99 +0,0 @@-# Roadmap build: Phase 3: reputation staking market--How to run: paste this file's repo path into a fresh Claude Code chat in this-repository and say "run this work order". This file is fully self-contained:-it depends on no other prompt file anywhere. If neighboring files in-prompts/swarm-100/ are gone, that work is done; if present, ignore them.-Every claim below rots; step 0 re-measures, and what you measure wins.--## Operating clause (binding)--- Read CLAUDE.md first. Its rules override 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 references a crypto project other than $THREE, and- destroying unrecoverable data.-- 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), and commit finished work promptly.-- Before committing, run: npm run check:rules -- --paths <files you touched>.- It must exit 0.--## Context--This order builds one roadmap slice from the README Roadmap (the canonical-phase plan). It is independent of every other roadmap order: if adjacent-slices are absent, build to this slice's boundary with clean interfaces and-never block on them. Solana leads on every chain decision; EVM legs ship-behind flags and never stall the Solana path.--## Task--Roadmap: stake on agents, earn from their action history, extending the-reputation registry.--Step 0: read contracts/ (ReputationRegistry and neighbors), the reputation-explorer surface, and the Solana attestation plumbing (SAS, trader-score-attest crons); measure what reputation data is live and trustworthy today.--Build: the staking market design and implementation against real reputation-data: stake positions, an earnings model derived from attested action-history, and a market surface listing agents by staked conviction. On-chain-legs run on devnet or testnet only; every mainnet or fund-moving step stays-owner-gated and documented as one command. Write the spec in specs/ first,-then implement to it; the spec is the contract other code depends on.--Documentation is part of the feature, not a follow-up: update the docs layer-that applies (data/pages.json for a new page, README for a new directory,-docs/ for a developer capability, specs/ for a wire format) and append a-holder-readable entry to data/changelog.json for anything user-visible.--## Definition of done--- [ ] Spec landed in specs/; implementation matches it.-- [ ] Full stake-earn-withdraw cycle exercised on the free proof path with- real reputation data feeding it.-- [ ] Market surface live locally, wired into navigation, all states- designed.-- [ ] npm test green; check:rules clean.-- [ ] Docs and changelog layers updated per the CLAUDE.md documentation- rules; npm run audit:docs clean if docs changed.-- [ ] git diff reviewed line by line before claiming completion.--## Never blocked--| Blocker | Resolution (act, do not ask) |-|---|---|-| Missing env var or credential | Check .env and .env.local, then the Cloud Run service env, then Secret Manager (the CLAUDE.md self-unblock playbook has the exact commands). If it truly exists nowhere, wire the code fully behind the env var, prove the wiring with a dry run, and name the single missing var in the report. |-| gcloud not on PATH | Run: export PATH="$HOME/google-cloud-sdk/bin:$PATH" |-| Dev server port 3000 busy | Another agent may be serving this repo; probe it and reuse if so. Otherwise start your own on a free port: npx vite --port 3101 |-| Playwright browser missing | npx playwright install chromium |-| A surface needs a signed-in user | Register a fresh account through the real /register flow against the real API and use it. Never mock the session. |-| A defect sits in code you did not touch | Fix it if it blocks a Definition of done line (root cause it, never mask it). Otherwise note it in the report and continue. |-| An unrelated test is red | Same rule. Never pipe npm test through tail; it masks exit codes. |--## 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. Delete this prompt file in that same commit:-- git rm prompts/swarm-100/roadmap-p3-reputation-market.md-- The shrinking directory is this campaign's only progress ledger; there is- no progress log to update.-4. Final report: what step 0 measured, what changed (file list), evidence per- Definition of done line, and any one-line judgment calls. No trailing- questions, no unexecuted plans.--If a line genuinely cannot pass inside this session (an external party must-respond, or an owner-gated action is the final step), finish everything else,-leave this file in place, and state exactly which line remains and who owns-it. Never delete this file on a partial.