Business operating system for Claude Code — 57 skills, 21 agents, smart daemon. Unified inbox (WhatsApp/Email/Slack/Telegram), autonomous PR merge, full-AWS monitoring, revenue (Stripe+RevenueCat), e-commerce (Shopify), marketing (Klaviyo/Meta/GA4), voice (Bland/ElevenLabs), APM (Datadog/NewRelic/OTEL), YOLO mode.
Shell agent-teamsai-agentai-automationanthropicautonomous-agentawsbusiness-operationsclaudeclaude-codeclaude-code-plugindevopsecommerceinbox-zeroklaviyomarketingmcpmorning-briefingpr-automationshopifyterminal
feat(ledger): wire 9 ops commands to Ops Ledger (directive B) (#364)
Aurora Capital38db2720cea4
diff --git a/claude-ops/skills/ops-comms/SKILL.md b/claude-ops/skills/ops-comms/SKILL.mdindex baf2d0a9..f0fd044f 100644--- a/claude-ops/skills/ops-comms/SKILL.md+++ b/claude-ops/skills/ops-comms/SKILL.md@@ -292,3 +292,42 @@ AskUserQuestion call 2 (only if "More..."):If all channels are configured, that's 6+ options — always batch. If only 3 channels are configured, "Read X" + "Read Y" + "Read Z" + "Send a message" = 4, fits in one call. The `voice` channel is configured iff `preferences.json` → `channels.voice` is present OR `default_channels` contains `"voice"`.Execute the selected action.++---++## Ledger Integration++**CLAIM_KEY by channel and message unit:**+- Slack thread: `slack:thread:<channel>:<ts>`+- WhatsApp message: `slack:thread:wa:<jid>:<ts>` (reuse slack: namespace for threads)+- Outbound draft (no inbound thread): `comms:draft:<channel>:<YYYY-MM-DDTHH-MM>`++### Pre-flight skip-check++```bash+CLAIM_KEY="slack:thread:<channel>:<ts>" # adjust per channel+ledger query --claim-key "$CLAIM_KEY" --since=-PT24H+```++Skip any message/thread where a `done` or `in_progress` entry exists. Surface+`awaiting_sam` entries as "draft already staged — resend or edit?"++### Claim + resolve++```bash+# Claim before drafting+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "draft" \+ --status "in_progress" \+ --title "Comms: <channel> — <brief description>" \+ --ttl-sec 3600++# After user approves + send fires+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "send" \+ --status "done" \+ --title "Comms: <channel> — <brief description>" \+ --context "sent via <channel>"+```diff --git a/claude-ops/skills/ops-deploy/SKILL.md b/claude-ops/skills/ops-deploy/SKILL.mdindex c35ea9a8..ac43505c 100644--- a/claude-ops/skills/ops-deploy/SKILL.md+++ b/claude-ops/skills/ops-deploy/SKILL.md@@ -218,3 +218,42 @@ When Vercel MCP tools are unavailable, use `WebFetch` with the Vercel API direct```WebFetch(url: "https://api.vercel.com/v6/deployments?projectId=<id>&limit=5", headers: {"Authorization": "Bearer $VERCEL_TOKEN"})```++---++## Ledger Integration++**CLAIM_KEY:** `deploy:<project>:<env>` (e.g. `deploy:my-api:production`)++Keyed on project + environment so concurrent deploys of the same target are blocked+for the full claim TTL (30 minutes).++### Pre-flight skip-check++```bash+CLAIM_KEY="deploy:<project>:<env>"+ledger query --claim-key "$CLAIM_KEY" --since=-PT24H+```++If `in_progress` exists, a concurrent deploy is already running — abort and surface+to the user. If `done` exists within the last hour, confirm before re-deploying.++### Claim + resolve++```bash+# Claim when deploy pipeline starts+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "file" \+ --status "in_progress" \+ --title "Deploy: <project> → <env>" \+ --ttl-sec 1800++# Resolve after deploy completes or fails+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "file" \+ --status "done" \+ --title "Deploy: <project> → <env>" \+ --context "succeeded|failed: <reason>"+```diff --git a/claude-ops/skills/ops-fires/SKILL.md b/claude-ops/skills/ops-fires/SKILL.mdindex 6315d70a..66b434b3 100644--- a/claude-ops/skills/ops-fires/SKILL.md+++ b/claude-ops/skills/ops-fires/SKILL.md@@ -291,3 +291,43 @@ The ops-daemon surfaces two additional fire categories in `daemon-health.json`:`/ops:fires` lists both alongside Sentry / infra / CI issues. Push notifications are dispatched by the daemon on the first crossing of the threshold — not re-sent until the next day (credentials) or window rollover (rate limits).+---++## Ledger Integration++**CLAIM_KEY:** `sentry:issue:<short_id>` (e.g. `sentry:issue:MY-PROJECT-1A2B`)++For non-Sentry fires (infra, CI, credential expiry), use:+- CI failure: `ci:run:<repo>:<run_id>`+- Credential expiry: `credential:expiry:<service>`++### Pre-flight skip-check++```bash+CLAIM_KEY="sentry:issue:<short_id>"+ledger query --claim-key "$CLAIM_KEY" --since=-PT24H+```++If `in_progress` or `done` exists, skip the issue. If `awaiting_sam` exists, surface+it as "fix already staged — needs your decision."++### Claim + resolve++```bash+# Claim when beginning to investigate/fix+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "fix" \+ --status "in_progress" \+ --title "Fire: <issue title>" \+ --ttl-sec 7200++# Resolve after fix is applied or escalated+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "fix" \+ --status "done" \+ --title "Fire: <issue title>" \+ --context "fixed: <brief resolution> | escalated: <reason>"+```+diff --git a/claude-ops/skills/ops-go/SKILL.md b/claude-ops/skills/ops-go/SKILL.mdindex 23952a8f..669a469d 100644--- a/claude-ops/skills/ops-go/SKILL.md+++ b/claude-ops/skills/ops-go/SKILL.md@@ -283,3 +283,42 @@ When `gog calendar` fails, use `WebFetch` with the Google Calendar API as fallba```WebFetch(url: "https://www.googleapis.com/calendar/v3/calendars/primary/events?timeMin=<today>T00:00:00Z&timeMax=<today>T23:59:59Z")```++---++## Ledger Integration++**CLAIM_KEY:** `daily-brief:<YYYY-MM-DD>` (e.g. `daily-brief:2026-05-28`)++### Pre-flight skip-check++Before generating the briefing, check whether one was already produced today:++```bash+BRIEF_DATE=$(date +%Y-%m-%d)+CLAIM_KEY="daily-brief:${BRIEF_DATE}"+ledger query --claim-key "$CLAIM_KEY" --since=-PT24H+```++If the query returns a `done` or `in_progress` entry, surface it to the user+("Briefing already ran today at HH:MM — rerun?") instead of re-fetching all sources.++### Claim + resolve++```bash+# Claim at briefing start+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "file" \+ --status "in_progress" \+ --title "Morning briefing ${BRIEF_DATE}" \+ --ttl-sec 86400++# Resolve after briefing is presented to the user+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "file" \+ --status "done" \+ --title "Morning briefing ${BRIEF_DATE}" \+ --context "N fires, N PRs, N unread"+```diff --git a/claude-ops/skills/ops-inbox/SKILL.md b/claude-ops/skills/ops-inbox/SKILL.mdindex dac7f53c..3aef2e40 100644--- a/claude-ops/skills/ops-inbox/SKILL.md+++ b/claude-ops/skills/ops-inbox/SKILL.md@@ -867,3 +867,50 @@ After processing, offer to schedule recurring inbox checks via `AskUserQuestion`[Schedule inbox check every 2 hours] [Schedule morning + evening] [No schedule]```Use `CronCreate` if selected. Show existing schedules with `CronList`.++---++## Ledger Integration++**CLAIM_KEY per thread:** `gmail:thread:<thread_id>`++Gmail threads are the primary unit. Each thread gets its own claim so parallel+agents or Perplexity don't process the same thread twice.++### Pre-flight skip-check (per thread)++```bash+CLAIM_KEY="gmail:thread:<thread_id>"+ledger query --claim-key "$CLAIM_KEY" --since=-PT24H+```++Skip threads where the query returns `in_progress` or `done`. Surface `awaiting_sam`+entries to the user as "already drafted — approve or rework?"++### Claim + resolve (per thread)++```bash+# Claim before drafting a reply+ledger write \+ --claim-key "gmail:thread:<thread_id>" \+ --kind "draft" \+ --status "in_progress" \+ --title "Reply: <subject>" \+ --ttl-sec 7200++# Resolve after draft is shown to user+ledger write \+ --claim-key "gmail:thread:<thread_id>" \+ --kind "draft" \+ --status "awaiting_sam" \+ --title "Reply: <subject>" \+ --context "Draft staged — awaiting approval"++# Resolve after user sends or skips+ledger write \+ --claim-key "gmail:thread:<thread_id>" \+ --kind "draft" \+ --status "done" \+ --title "Reply: <subject>" \+ --context "sent|skipped"+```diff --git a/claude-ops/skills/ops-linear/SKILL.md b/claude-ops/skills/ops-linear/SKILL.mdindex 2d2c1491..ce5b7dd5 100644--- a/claude-ops/skills/ops-linear/SKILL.md+++ b/claude-ops/skills/ops-linear/SKILL.md@@ -158,3 +158,39 @@ When Linear MCP tools hit quota limits or fail, fall back to `WebFetch` with the```WebFetch(url: "https://api.linear.app/graphql", method: "POST", headers: {"Authorization": "$LINEAR_API_KEY"}, body: '{"query":"{ issues(filter: {cycle: {id: {eq: \"<id>\"}}}}) { nodes { id title state { name } } } }"}')```++---++## Ledger Integration++**CLAIM_KEY:** `linear:issue:<identifier>` (e.g. `linear:issue:HEA-123`)++### Pre-flight skip-check++```bash+CLAIM_KEY="linear:issue:<identifier>"+ledger query --claim-key "$CLAIM_KEY" --since=-PT24H+```++If `in_progress` or `done` exists, skip — another session or Perplexity already+acted on this issue. Surface `awaiting_sam` entries as "update already staged."++### Claim + resolve++```bash+# Claim when creating, updating, or triaging a Linear issue+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "file" \+ --status "in_progress" \+ --title "Linear: <identifier> — <title>" \+ --ttl-sec 3600++# Resolve after Linear state is updated+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "file" \+ --status "done" \+ --title "Linear: <identifier> — <title>" \+ --context "status→<new_state> | assignee→<assignee>"+```diff --git a/claude-ops/skills/ops-merge/SKILL.md b/claude-ops/skills/ops-merge/SKILL.mdindex 29058ca1..79967135 100644--- a/claude-ops/skills/ops-merge/SKILL.md+++ b/claude-ops/skills/ops-merge/SKILL.md@@ -501,3 +501,39 @@ Create a `TaskCreate` for the overall merge pipeline and individual tasks per PR### WebSearch — CI failure contextWhen a fixer agent encounters an obscure CI failure, use `WebSearch` to find known issues (e.g., npm registry outages, GitHub Actions incidents, flaky test patterns).++---++## Ledger Integration++**CLAIM_KEY:** `gh:pr:<owner>/<repo>#<number>` (e.g. `gh:pr:your-org/your-repo#42`)++### Pre-flight skip-check++```bash+CLAIM_KEY="gh:pr:<owner>/<repo>#<number>"+ledger query --claim-key "$CLAIM_KEY" --since=-PT24H+```++If `done` exists, the PR was already merged or closed this session — skip. If+`in_progress` exists from another agent, do not attempt a concurrent merge.++### Claim + resolve++```bash+# Claim when beginning CI fix or merge flow for a PR+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "merge" \+ --status "in_progress" \+ --title "Merge: <repo>#<number> — <PR title>" \+ --ttl-sec 3600++# Resolve after merge completes or is skipped+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "merge" \+ --status "done" \+ --title "Merge: <repo>#<number> — <PR title>" \+ --context "merged|skipped: <reason>"+```diff --git a/claude-ops/skills/ops-triage/SKILL.md b/claude-ops/skills/ops-triage/SKILL.mdindex fd947c0e..3d1eaa91 100644--- a/claude-ops/skills/ops-triage/SKILL.md+++ b/claude-ops/skills/ops-triage/SKILL.md@@ -234,3 +234,42 @@ Use `WebSearch` to find known solutions for recurring errors (e.g., "AWS RDS con### LSP — code navigation for fix agentsWhen dispatching fix agents, use `LSP` to find symbol definitions, references, and call hierarchies. This helps agents navigate unfamiliar codebases faster than grep.++---++## Ledger Integration++**CLAIM_KEY by issue type:**+- Sentry: `sentry:issue:<short_id>`+- GitHub issue: `gh:pr:<owner>/<repo>#<number>` (reused for issues when no PR exists)+- Infra alert: `ci:run:<repo>:<run_id>`++### Pre-flight skip-check++```bash+CLAIM_KEY="sentry:issue:<short_id>" # adjust per issue type+ledger query --claim-key "$CLAIM_KEY" --since=-PT24H+```++Skip issues with `in_progress` or `done`. Present `awaiting_sam` issues at the+top of the triage board as "needs your decision."++### Claim + resolve++```bash+# Claim when opening a triage pass on an issue+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "fix" \+ --status "in_progress" \+ --title "Triage: <issue title>" \+ --ttl-sec 7200++# Resolve after fix dispatched or issue escalated+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "fix" \+ --status "done" \+ --title "Triage: <issue title>" \+ --context "fix dispatched|escalated|snoozed: <reason>"+```diff --git a/claude-ops/skills/ops-yolo/SKILL.md b/claude-ops/skills/ops-yolo/SKILL.mdindex 0f70b25e..88442ca8 100644--- a/claude-ops/skills/ops-yolo/SKILL.md+++ b/claude-ops/skills/ops-yolo/SKILL.md@@ -336,3 +336,44 @@ When YOLO dispatches fix agents or triggers deploys, use `Monitor` to stream CI### WebFetch/WebSearch — enrichmentUse `WebFetch` to pull Grafana dashboards, Sentry event details, or AWS status pages when MCPs are unavailable. Use `WebSearch` to find context on production errors (e.g., known AWS outages).++---++## Ledger Integration++**CLAIM_KEY:** `yolo:session` — one active YOLO session at a time (stable key for concurrency).++Individual actions within the session (merges, fixes, deploys) each write their own+typed claim via the relevant skill's ledger pattern (see `ops-merge`, `ops-fires`,+`ops-deploy`). The session-level key tracks the overall autonomous run.++### Pre-flight skip-check++```bash+SESSION_TS=$(date +%Y-%m-%dT%H-%M)+CLAIM_KEY="yolo:session"+ledger query --claim-key "$CLAIM_KEY" --since=-PT4H+```++If another YOLO session is `in_progress`, surface it before starting a new one —+two autonomous sessions running concurrently will conflict on shared resources.++### Claim + resolve++```bash+# Claim at YOLO session start+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "file" \+ --status "in_progress" \+ --title "YOLO session ${SESSION_TS}" \+ --ttl-sec 14400++# Resolve at session end with summary+ledger write \+ --claim-key "$CLAIM_KEY" \+ --kind "file" \+ --status "done" \+ --title "YOLO session ${SESSION_TS}" \+ --context "N fires fixed, N PRs merged, N deploys triggered"+```