mirror of
https://github.com/Kpa-clawbot/meshcore-analyzer.git
synced 2026-07-17 10:42:30 +00:00
df28efaed9
## What Adds `docs/agents/` — an onboarding pack for external contributors using their own AI coding agent (Claude Code, Codex, Cursor, Aider, OpenClaw, etc.). ## Why Maintainers run an agent-driven workflow against this repo. External contributors using agents benefit from the same discipline (TDD red→green, PII preflight, parallel persona polish, three-axis merge readiness) but had nothing portable to point at. This documents the **process** and the **reusable building blocks** in an agent-agnostic way. ## Contents ``` docs/agents/ README.md WORKFLOW.md # pipeline + planning + PII preflight + force-push + worktrees RULES.md # 36 hard-won discipline rules TDD.md # red→green requirement, exemptions SUBAGENT-BRIEF-TEMPLATE.md skills/ # 14 task playbooks (intake, fix, polish, merge-gate, release, ops...) personas/ # 14 review voices (carmack, dijkstra, torvalds, meshcore, taleb, ...) ``` ## Scope Docs-only. No code changes. Existing `AGENTS.md` is unchanged. All committed text uses sanitized placeholders (`<workspace>`, `<repo>`, `YOUR_NAME`, `YOUR_HANDLE`, etc.) — no personal names, phones, IPs, keys, or absolute home/root paths. ## Verification - PII preflight grep on staged diff: only matches are the literal placeholders inside the documented sanitized example (`YOUR_NAME|YOUR_HANDLE|...|api[_-]?key|...`). - Off-topic skill grep on `docs/agents/`: clean (zero hits for the wrong-language/off-topic skill names that were scrubbed from the prior attempt). --------- Co-authored-by: meshcore-bot <bot@meshcore.local> Co-authored-by: Kpa-clawbot <bot@openclaw.local> Co-authored-by: efiten <erwin.fiten@gmail.com>
Skills
Skills are task-specific playbooks an agent can load when it gets a particular kind of request. Each file here is self-contained — name, description/triggers, inputs, steps, output format, and failure modes.
These are written in a structure we use internally, but the shape is portable: you can paste any of these into a Claude Code / Codex / Cursor / Aider / OpenClaw system prompt or rule file and the agent will follow it.
Index
Intake & triage
- bug-intake — diagnose a bug with expert personas; identify root causes, severity.
- feature-intake — refine a vague feature request into a locked, implementable spec.
- triage-sweep — bulk-categorize open issues across multiple lanes.
Implementation
- fix-issue — end-to-end issue fix: implement, open PR, watch CI, auto-fix, hand off to polish.
- debug-repro — reproduce bugs locally against fixture/staging before fixing.
PR pipeline
- ci-watcher — lightweight watcher that polls CI checks and notifies on flip.
- pr-preflight — pre-submission gate of fast fail-fast greps (run BEFORE
gh pr create). - pr-polish — adversarial + expert + Kent-Beck review fan-out in parallel.
- pr-merge-gate — three-axis pre-merge check (mergeable + CI + reviews).
Release & ops
- corescope-release — release tag + deploy + verification flow.
- devops-fix — live operational fixes on staging/prod (SSH, docker, sqlite, log triage).
- qa-suite — full QA sweep against a running instance.
Language-specific quality gates
- go-style-enforcer — Google Go style guide enforcement on Go diffs.
Meta
- subagent-brief-template — the template every subagent brief must follow.
Adapting these to your agent
- The skills assume a
read/edit/execstyle tool surface and aghCLI. Substitute whatever your harness uses. - Trigger phrases are suggestions; map them to your harness's slash-command or rule-matching system.
- Paths inside the skills use placeholders like
<workspace>,<repo>,<home>— replace with your actual layout.