Skip to content

Junhanliu-dev/espalier-engineering / skills/espalier-init

espalier-init

Verified

Analyze any existing codebase, discover its patterns and best practices, and generate an Espalier structure (rules, skills, wiki, pipeline) so AI coders produce code matching that project's language and conventions. Greenfield repos take the two-pass Decide-Then-Bind path (/espalier-map charts the conventions, init binds them); boilerplate repos run init normally, then map the product. Wires into Claude Code, Codex, and/or GitHub Copilot (.claude/, .agents/skills/ + .codex/, .github/).

FileKindSize
SKILL.mdskill md43.5 KB
hook-templates/check-layer-boundaries-go.shscript665 B
hook-templates/check-layer-boundaries-python.shscript821 B
hook-templates/check-layer-boundaries-typescript.shscript1.6 KB
hook-templates/copilot-hook-adapter.shscript2.4 KB
hook-templates/drift-detect.shscript5.7 KB
hook-templates/drift-helpers.shscript56.4 KB
hook-templates/espalier-outside.shexecutablescript28.8 KB
hook-templates/espalier-pr.shexecutablescript43.2 KB
hook-templates/espalier-stats.shexecutablescript27.3 KB
hook-templates/lookup-helpers.shscript9.5 KB
hook-templates/map-guard.shexecutablescript3.9 KB
hook-templates/maprun-dispatch.shexecutablescript21.0 KB
hook-templates/maprun-integration.shexecutablescript3.4 KB
hook-templates/maprun-merge.shexecutablescript2.9 KB
hook-templates/maprun-pr.shexecutablescript12.8 KB
hook-templates/maprun-verify.shexecutablescript5.0 KB
hook-templates/maprun.pyscript65.6 KB
hook-templates/parse-drift-blocks.pyscript1.1 KB
hook-templates/post-edit-wrapper.shscript2.0 KB
hook-templates/post-merge-backlink.shscript2.2 KB
hook-templates/pre-push-gate-wrapper.shscript3.0 KB
hook-templates/pre-push-gate.shscript18.1 KB
hook-templates/rebuild-commit-index.shscript2.6 KB
references/discovery-checklist.mdmarkdown18.5 KB
references/validation.mdmarkdown16.7 KB
references/wiki-templates.mdmarkdown710 B
references/wiring.mdmarkdown13.5 KB
templates/agent.mdmarkdown3.7 KB
templates/agents/harness-coder.mdmarkdown33.9 KB
templates/agents/harness-reviewer.mdmarkdown25.1 KB
templates/agents/harness-security.mdmarkdown14.0 KB
templates/agents/modes/fix-round.mdmarkdown3.0 KB
templates/agents/modes/re-review.mdmarkdown5.3 KB
templates/agents/modes/repo-audit.mdmarkdown2.8 KB
templates/agents/modes/simplification.mdmarkdown7.0 KB
templates/agents/modes/stage6-abuse-coverage.mdmarkdown1.3 KB
templates/agents/modes/wiki-sweep.mdmarkdown5.6 KB
templates/pipeline.mdmarkdown18.9 KB
templates/rules/coding-standards.mdmarkdown3.2 KB
templates/rules/development-process.mdmarkdown3.2 KB
templates/rules/engineering-structure.mdmarkdown1008 B
templates/rules/production-standards.mdmarkdown5.8 KB
templates/rules/security-standards.mdmarkdown5.6 KB
templates/scout-prompts.mdmarkdown9.0 KB
templates/skills/espalier-ask.mdmarkdown6.4 KB
templates/skills/espalier-audit.mdmarkdown10.0 KB
templates/skills/espalier-coding-references/platform-native.mdmarkdown9.4 KB
templates/skills/espalier-coding-spec.mdmarkdown496 B
templates/skills/espalier-coding.mdmarkdown4.0 KB
templates/skills/espalier-doctor.mdmarkdown8.0 KB
templates/skills/espalier-fix.mdmarkdown77.5 KB
templates/skills/espalier-grill.mdmarkdown21.5 KB
templates/skills/espalier-map.mdmarkdown20.0 KB
templates/skills/espalier-maprun.mdmarkdown31.1 KB
templates/skills/espalier-prune.mdmarkdown13.0 KB
templates/skills/espalier-repot.mdmarkdown7.6 KB
templates/skills/espalier-requirements.mdmarkdown4.7 KB
templates/skills/espalier-review.mdmarkdown4.5 KB
templates/skills/espalier-security.mdmarkdown5.6 KB
templates/skills/espalier-simplify.mdmarkdown25.0 KB
templates/skills/espalier-stages/1-2-requirements.mdmarkdown7.6 KB
templates/skills/espalier-stages/3-coding.mdmarkdown15.0 KB
templates/skills/espalier-stages/4-panel.mdmarkdown14.3 KB
templates/skills/espalier-stages/5-6-contract.mdmarkdown10.3 KB
templates/skills/espalier-stages/7-10-delivery.mdmarkdown16.8 KB
templates/skills/espalier-stages/simple.mdmarkdown14.0 KB
templates/skills/espalier-testing.mdmarkdown2.9 KB
templates/skills/espalier.mdmarkdown27.7 KB

references/validation.md

View on GitHub
# Phase 11: Validation (Dry Run)

> **v0.4.0+ note:** Phase 11 runs via `scripts/bootstrap-espalier.sh` (Stage 11 of that script — 60 checks when only claude is targeted, 65 with codex, 70 with copilot: all but #25 in parallel, #25 run serially so its per-tier table reaches stdout). Normal flow invokes this automatically. Manual usage: `bash scripts/bootstrap-espalier.sh --validate-only --plugin-dir=...` to re-run only the validation block (e.g., after manual file edits); add `--ignore-drift` to downgrade check #25's expired-drift hard fail to a logged override.
>
> **Platform gating (v0.14.0/v0.15.0):** the platform set comes from `--platforms` unioned with `espalier/.platforms`. When claude is NOT targeted, checks 1-5 and 8 report `OK … (skipped — claude not targeted)`, and checks 13/14/29-33/35 swap their `.claude/…` paths for the `espalier/…` source equivalents. Checks 47-51 run when codex is targeted (skip-rendered when only copilot forces the range); checks 52-56 run only when copilot is targeted. Checks 57-70 are unconditional base checks appended after the platform blocks (base numbering 1-46, 57-70 — non-contiguous so shipped platform IDs stay stable). Claude-only installs print exactly 60 lines.

> **This table mirrors bootstrap-espalier.sh Stage 11 — update BOTH in the same commit.**

After all generation and wiring is complete, validate end-to-end.

## Final Wiring Verification

| # | Check name | What it runs | How to fix a failure |
|---|-----------|--------------|----------------------|
| 1 | rules-load | `ls .claude/rules/espalier-*.md` | Re-run bootstrap Stage 5 (`--wire-only`) to recreate the rule symlinks |
| 2 | skills-load | `ls -d .claude/skills/espalier-coding … espalier-audit` (all 15 skill symlinks, incl. bare `espalier`) | Re-run bootstrap Stage 5; a missing source folder means the Phase 2/Stage 3 write was skipped |
| 3 | agents-load | `ls .claude/agents/harness-coder.md harness-reviewer.md harness-security.md` | Re-run bootstrap Stage 5; missing source = Phase 2 agent write skipped |
| 4 | hooks-configured | `grep -q "espalier/hooks" .claude/settings.json` | Re-run bootstrap Stage 8 (settings merge) |
| 5 | symlinks-valid | `[ -L .claude/rules/espalier-structure.md ] && [ -e … ]` | Broken link → the target rule file is missing; re-run Phase 2 write, then Stage 5 |
| 6 | hooks-executable | `test -x` post-edit-wrapper.sh, pre-push-gate.sh, pre-push-gate-wrapper.sh | `chmod +x espalier/hooks/*.sh` (bootstrap Stage 4 does this) |
| 7 | state-template | `test -f espalier/changes/_template/pipeline-state.md` | Re-run bootstrap Stage 6 |
| 8 | claudemd-updated | `grep -q "## Espalier" CLAUDE.md` | Re-run bootstrap Stage 7 |
| 9 | espalier-agent-md | `test -f espalier/agent.md` | Re-run espalier-init Phase 2 (agent.md write) |
| 10 | espalier-pipeline-md | `test -f espalier/pipeline.md` | Re-run bootstrap Stage 3 (pure copy) |
| 11 | skill-name-parity | every `espalier/skills/*/SKILL.md` folder name == its `name:` frontmatter | Rename the folder or fix the frontmatter so they match |
| 12 | typed-changes-dirs | `[ -d espalier/changes/feat ] && fix && refactor` | Re-run bootstrap Stage 2 (mkdir) |
| 13 | espalier-fix-skill | `test -f .claude/skills/espalier-fix/SKILL.md` | Re-run bootstrap Stages 3 + 5 |
| 14 | espalier-fix-name | `grep -q "^name: espalier-fix" .claude/skills/espalier-fix/SKILL.md` | The copied template is stale/edited — recopy from the plugin |
| 15 | rules-engineering | `test -f espalier/rules/engineering-structure.md` | Re-run espalier-init Phase 2 |
| 16 | rules-standards | `test -f espalier/rules/coding-standards.md` | Re-run espalier-init Phase 2 |
| 17 | merge-decision | `.merge-hook-decision` is one of the six accepted values | Rewrite the file with a valid value (or re-run bootstrap Stage 9) |
| 18 | hook-template-copy | `test -f && test -x espalier/hooks/post-merge-backlink.sh` | Re-run bootstrap Stage 4 |
| 19 | lookup-helpers | `test -f espalier/hooks/lookup-helpers.sh` | Re-run bootstrap Stage 4 |
| 20 | post-merge-dispatcher | `ESPALIER_POSTMERGE_DISPATCH` present in git's real hooks dir (`core.hooksPath` honored) or `.husky/post-merge` | Re-run bootstrap Stage 9; if `core.hooksPath` points outside the repo, bootstrap refuses and warns — fix the config first |
| 21 | rebuild-script | `test -x espalier/hooks/rebuild-commit-index.sh` | Re-run bootstrap Stage 4 |
| 22 | gitignore-cache | `grep -qxF "espalier/.commit-index.tsv" .gitignore` | Re-run bootstrap Stage 10 |
| 23 | rebuild-runs | `bash espalier/hooks/rebuild-commit-index.sh && test -f espalier/.commit-index.tsv` | Read the script's stderr — usually a malformed pipeline-state.md |
| 24 | cache-tsv-format | every populated `.commit-index.tsv` row has 4 tab-separated fields | Delete the cache and re-run the rebuild script |
| 25 | stale-tiers (serial — `run_check_25`) | reads `espalier/.drift-state.tsv`; per-tier table; fails only on expired (>90d) artifacts | Run `/espalier-prune --all-stale`, or `--ignore-drift` to log an override |
| 26 | drift-state-format | every populated `.drift-state.tsv` row has 4 tab-separated fields | Fix or delete the malformed row (see `.drift.log` for its origin) |
| 27 | conventions-format | every populated `.conventions.tsv` row has 5 or 6 tab-separated fields | Fix or delete the malformed row |
| 28 | doctor-cadence | `.doctor-cadence` absent, or `cadence:` is a known value | Rewrite the file (`cadence: weekly` etc.) |
| 29 | espalier-ask-skill | `test -f .claude/skills/espalier-ask/SKILL.md` | Re-run bootstrap Stages 3 + 5 |
| 30 | security-rule | `[ -L .claude/rules/espalier-security.md ] && [ -e … ]` | Re-run Phase 2 (security-standards.md) + Stage 5 |
| 31 | security-agent | `test -f .claude/agents/harness-security.md` | Re-run Phase 2 agent write + Stage 5 |
| 32 | security-skill | `test -f .claude/skills/espalier-security/SKILL.md` | Re-run Phase 2 write + Stage 5 |
| 33 | audit-skill | `test -f .claude/skills/espalier-audit/SKILL.md` | Re-run bootstrap Stages 3 + 5 |
| 34 | audit-mode (body heading + `modes/repo-audit.md`) | `grep -qF "## Repo-Audit Mode" espalier/agents/harness-security.md` | The agent file is stale — re-run Phase 2 from the current template |
| 35 | production-rule | `[ -L .claude/rules/espalier-production.md ] && [ -e … ]` | Re-run Phase 2 (production-standards.md) + Stage 5 |
| 36 | production-file | `test -f espalier/rules/production-standards.md` | Re-run espalier-init Phase 2 |
| 37 | scout-prompts | `test -f espalier/.scout-prompts.md` | Re-run bootstrap Stage 3 |
| 38 | phase2-coding-skill | `test -f espalier/skills/espalier-coding/SKILL.md` | Re-run espalier-init Phase 2 (LLM write) |
| 39 | phase2-review-skill | `test -f espalier/skills/espalier-review/SKILL.md` | Re-run espalier-init Phase 2 (LLM write) |
| 40 | phase2-testing-skill | `test -f espalier/skills/espalier-testing/SKILL.md` | Re-run espalier-init Phase 2 (LLM write) |
| 41 | wiki-architecture | `test -f espalier/wiki/architecture.md` | Re-run espalier-init Phase 2 (scout 1.2 → wiki write) |
| 42 | wiki-data-models | `test -f espalier/wiki/data-models.md` | Re-run espalier-init Phase 2 (scout 1.8 → wiki write) |
| 43 | wiki-critical-paths | `test -f espalier/wiki/critical-paths.md` | Re-run espalier-init Phase 2 (scout 1.9 → wiki write) |
| 44 | wiki-external-services | `test -f espalier/wiki/external-services.md` | Re-run espalier-init Phase 2 (scout 1.10 → wiki write) |
| 45 | rules-development-process | `test -f espalier/rules/development-process.md` | Re-run espalier-init Phase 2 (LLM write) |
| 46 | layer-boundaries-hook | `test -f && test -x espalier/hooks/check-layer-boundaries.sh` | Phase 2 writes it for typescript/python/go; `--lang=unsupported` makes bootstrap write a no-op; `chmod +x` if present but not executable |
| 47 | codex-skills-load *(codex only)* | `ls -d .agents/skills/espalier-coding … espalier-audit` (all 15 skill symlinks) | Re-run bootstrap Stage 5 with `--platforms=codex` (or `claude,codex`) |
| 48 | codex-symlinks-valid *(codex only)* | `[ -L .agents/skills/espalier ] && [ -e … ]` | Broken link → source skill folder missing; re-run Stage 3/Phase 2, then Stage 5 |
| 49 | codex-agents-toml *(codex only)* | `name = "harness-…"` present in all three `.codex/agents/harness-*.toml` | Re-run bootstrap Stage 8c (delete the bad file first — stage is write-if-absent) |
| 50 | codex-hooks-configured *(codex only)* | `grep -q "espalier/hooks" .codex/config.toml` | Re-run bootstrap Stage 8b; if a stale `ESPALIER HOOKS` marker exists without the commands, delete the block and re-run |
| 51 | codex-agentsmd *(codex only)* | `grep -q "## Espalier" AGENTS.md` | Re-run bootstrap Stage 7b |
| 52 | copilot-skills-load *(copilot only)* | `ls -d .github/skills/espalier-coding … espalier-audit` (all 15 skill symlinks) | Re-run bootstrap Stage 5 with copilot in `--platforms` |
| 53 | copilot-symlinks-valid *(copilot only)* | `[ -L .github/skills/espalier ] && [ -e … ]` | Broken link → source skill folder missing; re-run Stage 3/Phase 2, then Stage 5 |
| 54 | copilot-agents *(copilot only)* | `name: harness-…` present in all three `.github/agents/harness-*.agent.md` | Re-run bootstrap Stage 8d (delete the bad file first — stage is write-if-absent) |
| 55 | copilot-hooks-json *(copilot only)* | `espalier-gates.json` parses as JSON, references `copilot-hook-adapter`, and the adapter is executable | Re-run bootstrap Stage 8e (delete the bad file first); `chmod +x espalier/hooks/copilot-hook-adapter.sh` |
| 56 | copilot-instructions *(copilot only)* | `grep -q "## Espalier" .github/copilot-instructions.md` | Re-run bootstrap Stage 7c |
| 57 | gitattributes-union | `grep -qxF "espalier/.ask-gaps.tsv merge=union" .gitattributes` | Re-run bootstrap Stage 10 (the only shipped union attribute — never add one for .conventions.tsv or .doctor-stamp) |
| 58 | canonical-ref-keys | `canonical-remote:` + `canonical-branch:` non-empty in `espalier/.espalier-config` | Re-run bootstrap Stage 9 (appends missing keys; preserves present values) |
| 59 | map-skill | `.claude/skills/espalier-map/SKILL.md` present with `name: espalier-map` | Re-run bootstrap Stages 3 + 5 |
| 60 | map-guard | `espalier/hooks/map-guard.sh` executable and registered in `.claude/settings.json` | Re-run bootstrap Stages 4 + 8 |
| 61 | maprun-skill | `.claude/skills/espalier-maprun/SKILL.md` present with `name: espalier-maprun` | Re-run bootstrap Stages 3 + 5 |
| 62 | maprun-engine | `maprun.py` present; `maprun-{dispatch,merge,integration,verify}.sh` executable | Re-run bootstrap Stage 4 (engine files are write-if-absent — delete a broken one first) |
| 63 | simplify-skill | `.claude/skills/espalier-simplify/SKILL.md` present with `name: espalier-simplify` | Re-run bootstrap Stages 3 + 5 |
| 64 | context-helpers | `drift-helpers.sh` defines `report_archive`, `contract_extract`, `exit_gate`, `grep_only_files`, `scoped_docs`; `grep-only-paths:` in `espalier/.espalier-config` | Re-run bootstrap Stage 4 (hooks) + Stage 9 (config append-if-missing) — or migration #35 |
| 65 | spawn-protocols | coder template carries `## Handoff`, `- HANDOFF: true`, `- Spec applied:`, `## Commit Discipline`; reviewer carries `[spec-unread]`; the espalier stage files + fix SKILL grep the sentinel and their pack templates carry `- Scoped docs:`; no `≤ 5 files` in espalier-requirements, no `≤ 8` read budget in espalier-grill / espalier-map (greenfield Pass 1: pending) | Re-run espalier-init Phase 2 for the agents; Stage 3 for the skills — or migration #35 (a customised agent file missing its anchor is recorded in `espalier/.migrations-skipped`) |
| 66 | stage-procedures | every `espalier/skills/espalier/stages/{1-2-requirements,3-coding,4-panel,5-6-contract,7-10-delivery}.md` present and named by the router's Stage Execution Protocol; every `espalier/agents/modes/{fix-round,simplification,re-review,repo-audit,stage6-abuse-coverage}.md` present and named on a prompt line in the stage files / fix SKILL / audit SKILL | Re-run bootstrap Stage 3 (pure copies) — or migration #35 |
| 67 | turn-economy-helpers | `drift-helpers.sh` defines `contract_gaps`, `certificate_write`, `record_commits`, `drift_index`, `stage85_drift`, `backlink_all`, `regression_verify`, `_gate_scope_line`; the espalier stage files + fix SKILL call them by name | Re-run bootstrap Stage 4 (hooks) + Stage 3 (pure copies) — or migration #36 |
| 68 | contract-coverage | security template's contract entries carry `covered_by:`; coder carries `Abuse test, now` + `## Verify in One Call`; `modes/stage6-abuse-coverage.md` verifies `covered_by`; the stage files + fix SKILL carry `- Session-Boundary:` and `GAPS:` (greenfield Pass 1: pending) | Re-run espalier-init Phase 2 for the agents; Stage 3 for the skills — or migration #36 (a customised agent file missing its anchor is recorded in `espalier/.migrations-skipped`) |
| 69 | unknowns-channel | `drift-helpers.sh` defines `deviations_list`, `open_question_append`, `delivery_brief`, `_md_section`; the grill carries `Step 1.6`, espalier-requirements `## References`; the coder carries `### Deviations` + `- BLOCKED-ON-REQUIREMENT:`, the reviewer `[deviation]`, the auditor reads `### Deviations`; the stage files + fix SKILL carry `BLOCKED-ON-REQUIREMENT`, `deviations_list`, `delivery_brief` (greenfield Pass 1: pending) | Re-run bootstrap Stage 4 (hooks) + Stage 3 (pure copies); espalier-init Phase 2 for the agents — or migration #37 (a customised agent file missing its anchor is recorded in `espalier/.migrations-skipped`) |
| 70 | ceiling-ledger | `espalier/skills/espalier-coding/references/platform-native.md` present (the ladder's rung-4 lookup); `espalier-stats.sh` carries the `ceilings: markers=` ledger; the simplify SKILL hands scouts `CEILING MARKERS`; the grill counts `Over-specified mechanism`; the coder carries the `ceiling:` marker rule and names `platform-native.md`; the reviewer carries `[ceiling]` and `shrink:` (greenfield Pass 1: pending) | Re-run bootstrap Stage 3 (pure copies) + Stage 4 (hooks); espalier-init Phase 2 for the agents — or migration #38 (a customised agent file missing its anchor is recorded in `espalier/.migrations-skipped`) |

**Outside mode (v0.30, `--outside` / `/espalier-repot`)** keeps every check
number and total; the checks that read a tracked file read its local-only
counterpart instead: 4 and 60 read `.claude/settings.local.json`, 8 reads
`CLAUDE.local.md`, 22 asserts `/espalier` in `.git/info/exclude` and a symlink
resolving into a root whose `.espalier-origin` names this project, 57 asserts
`outside-root:` names a directory with its own `.git` and `.espalier-origin`,
and 20 / 50 / 51 / 56 also accept a path recorded in `espalier/.outside-skipped`
(a tracked instruction or hook file bootstrap left alone). Checks 2 / 47 / 52
include the `espalier-repot` skill link.

When copilot is targeted WITHOUT codex, checks 47-51 print as `OK … (skipped — codex not targeted)` so numbering stays contiguous; totals: 60 (claude-only) / 65 (+codex) / 70 (+copilot); 57-70 run on every platform set.

**Policy 3 — staleness tiers (check #25):** an artifact's age is measured from
its `stale_first_seen` timestamp — fresh (<14d, silent), aging (14–30d, INFO),
stale (30–60d, WARN), critical (60–90d, loud WARN), expired (>90d, check #25
fails). Thresholds are hardcoded in v1.

## End-to-End Checks

1. **Trace a simple requirement** through all 10 stages mentally
2. **Verify all cross-references resolve:**
   - pipeline.md references skills → skills exist
   - agent.md references rules → rules exist
   - coding SKILL.md references specs → specs exist
   - sub-agents reference skills → skills exist
   - **every skill folder name equals its SKILL.md `name:` frontmatter**
3. **Check for contradictions:**
   - coding-standards.md vs. layer specs (no conflicts?)
   - pipeline gates vs. development-process (aligned?)
4. **Test hooks:**
   - Create a file violating layer boundaries → hook blocks (exit 2, stderr)
   - Attempt push at Stage 2 → gate blocks (exit 2, stderr)
5. **Session resumption test:**
   - Create a pipeline-state.md at Stage 3
   - Run `/espalier` → it should resume, not restart

## Manual Integration Tests (run after generation + wiring)

Quick summary:

| Test | Purpose | Tripwire |
|------|---------|----------|
| A | Causal-link round-trip | Fix's caused_by → causing feat's Follow-up Fixes |
| B | Stage 1/3 escalation | Rename + reset + tombstone |
| C | Pre-push gate | Blocks at Stage <7, passes at ≥7 |
| D | Squash hook recording | post-merge writes `squashed_to:` row |
| E | Squash skip-only path | Marks `unknown_squash`, fix proceeds |
| F | ask-later fallback | Orchestrator prompt fires once; subsequent invocations silent |
| G | Reverse-lookup cache | Cold scan auto-builds; Layer 0 hit on second invocation; --no-index bypass; --rebuild-index works |

Report: "Espalier validated. {N} checks passed, {M} issues found: {list}"
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 321kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall