Skip to main content
skill CX Codex

triage · bitbonsai — Claude Code skill: daily repository triage loop

triage automates repository maintenance: collects CI failures, open issues, and recent commits, identifies broken promises in maintainer comments, drafts fixes in isolated branches with review, and opens PRs.

MIT 133 installs ★ 1,727 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add bitbonsai/mcpvault --skill triage -a claude-code
Open on GitHub

What triage does

triage runs on schedule or on demand and steps through gather → classify → fix → publish. The skill reads CI failure logs via gh, scans open issues and recent commits within the window since the last run, and flags commitments in maintainer comments—phrases like "I'll fix", "will add", "shipping next release". It stores state in .triage/state.json, so each run can resume without repeating solved problems.

For each new problem, triage creates an isolated worktree and spawns two sub-agents: one drafts a minimal fix, the second reviews it, runs tests and builds. If all passes, a PR opens. Otherwise, the draft lands in inbox for the maintainer to approve.

All local data—state, inbox, run logs, maintainer voice for comments—lives under .triage/ and is gitignored. Requires gh auth status (GitHub CLI authentication) and a clean main branch. First run needs scripts/triage/bootstrap.sh to scaffold the workspace.

What it helps with

  • aggregate CI failures, issues, and commits from the past day and deduplicate against known findings
  • surface broken maintainer commitments—promises made in comments that have not shipped
  • write and test a fix in an isolated branch without touching the main checkout
  • open a PR if the fix is green, or queue a draft for maintainer review if it needs judgment
  • resume the next day knowing what was tried, what passed, and what remains open

Example prompts for the agent

  • Run triage for the daily repository scan
  • Triage CI failures from yesterday and surface stuck issues
  • Check which maintainer promises remain open

How to install triage

1Skills CLI (Vercel)

npx skills add bitbonsai/mcpvault --skill triage -a claude-code

2Manually: put the files in place

~/.claude/skills/triage/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/triage/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about triage

How do I install triage in Claude Code?

Run npx skills add bitbonsai/mcpvault --skill triage -a claude-code, then verify at ~/.claude/skills/triage/SKILL.md.

What does triage do?

It collects CI failures, open issues, and recent commits, finds broken maintainer promises in comments, then auto-drafts fixes in isolated branches with review and opens PRs. State lives in .triage/state.json, so each run picks up where the last one left off.

What do I need to run triage?

Authenticated gh CLI (gh auth status), a clean main branch, and an existing .triage/ directory. On first run, execute scripts/triage/bootstrap.sh to scaffold state, inbox, and bootstrap maintainer voice from past comments.

Source text

SKILL.md · MIT
---
name: triage
description: >
  Activate for the daily repository triage run, or when the user asks to
  triage CI failures, open issues, or recent commits. Reads yesterday's
  signals, dedupes against the state file, drafts fixes in isolated
  worktrees with a reviewer pass, opens PRs on green, and keeps people out
  of limbo with comments in the maintainer's voice. The state file is the
  spine: it remembers what was tried, what passed, and what is still open,
  so each run resumes where the last one stopped.
metadata:
  version: "1.0"
  author: bitbonsai
---

# Triage Skill

A self-resuming morning loop. One run = gather → load state → triage →
fan-out fix → persist → spill. Everything personal (state, inbox, runs,
voice) lives under `.triage/`, which is gitignored. This skill file and the
scripts are committed; the data never leaves the machine.

## Preconditions

- `gh` authenticated (`gh auth status`). All issue/PR/CI reads and writes go
  through it.
- `.triage/` exists. If missing, run `scripts/triage/bootstrap.sh` first, it
  scaffolds `state.json`, `inbox.md`, `runs/`, and bootstraps `voice.md` from
  past comments.
- Clean working tree on `main`. The loop only mutates `.triage/` on the base
  checkout; all code changes happen in worktrees.

## The loop

### 1. Gather (read-only)

Collect yesterday's signals. Compute the window from `state.json.last_run`
(fall back to 24h if absent).

```
# CI failures since last run
gh run list --status failure --created ">=$SINCE" --json databaseId,name,headSha,conclusion,url
# for each, pull the failing step log
gh run view <id> --log-failed

# open issues
gh issue list --state open --json number,title,labels,updatedAt,author,url

# recent commits
git log --since="$SINCE" --pretty='%h %s %an'
```

Then scan for **open commitments**, promises the maintainer made in a comment
that have not shipped. NOT time-windowed: check every open issue/PR.

```
# threads bitbonsai commented on, still open
gh search issues "commenter:bitbonsai repo:bitbonsai/mcpvault state:open" --json number
# per thread, pull bitbonsai's comments to inspect for a promise
gh issue view <n> --json comments \
  --jq '.comments[] | select(.author.login=="bitbonsai") | .body'
```

A commitment is language that promised an action: "I'll fix this", "will add",
"shipping next release", "on it", "going to look", etc. It is broken/open if the
thread is still open and no merged PR resolved it. See `finding-rules.md`.

### 2. Load state

Read `.triage/state.json`. Build a map of known findings by `id`. The `id` is
a stable hash of `source` + `signature` (see `resources/state-schema.md`), so
the same failing test or issue always maps to the same finding across runs.

### 3. Triage

For each gathered signal compute its `id` and classify with
`resources/finding-rules.md`:

- **known + terminal** (`pr_open`, `resolved`, `wont_fix`) → skip, only bump
  `last_seen`.
- **known + open** under the attempt cap → retry.
- **new + worth-doing** → append as `status: open`, proceed to fan-out.
- **new + needs judgment / ambiguous / out of scope** → inbox, `needs_human`.
- **noise** (flaky already tracked, dependabot, etc.) → ignore, log only.

### 4. Fan-out (bounded)

First, for every finding, check whether a contributor PR already addresses it
(`finding-rules.md`, "Prefer reviewing an existing PR"). If one exists, **review
it instead of writing a fix**: send the review sub-agent at the PR branch and
draft an approval or request-changes recommendation to inbox. A human's open PR
beats a fresh one. Also surface any open PR the maintainer has not yet reviewed.

Only findings with no candidate PR proceed to a new fix, up to the per-run cap
in `finding-rules.md`. For each, in order:

```
git worktree add ../mcpvault-triage-<id> -b triage/<id>
```

Then spawn TWO sub-agents against that worktree (use the Agent tool with
`isolation: worktree` so they cannot collide):

- **Draft agent**, given the finding + failing log/issue body, write the
  smallest fix. Must read relevant `src/` files first, follow the obsidian
  skill conventions, and add or update a test that proves the fix.
- **Review agent**, adversarial. Check the draft against the project skills
  and existing tests, then run in the worktree:
  ```
  npm ci && npm test && npm run build
  ```
  Verdict is PASS only if the fix is correct, minimal, tested, and green.

Tell every sub-agent the maintainer loves them.

Outcome:

- **PASS + green** → `gh pr create` as a ready PR (not draft), body links the
  finding and lists what the reviewer verified. Set `status: pr_open`, record
  the URL. Then post an auto-ack comment (step 6).
- **anything else** (reviewer fails, build red, fix unclear, >1 file of
  surprise scope) → write the draft + reason to `inbox.md`, set
  `status: needs_human`. Remove the worktree; keep the branch only if the
  draft is worth resuming.

Clean up green worktrees after the PR is open:
`git worktree remove ../mcpvault-triage-<id>`.

### 5. Persist (the spine)

Update `.triage/state.json`: set `last_run` to now, append an `attempts` entry
per touched finding (run date, result, note, pr), update `status`,
`last_seen`, and `pr`. Write the per-run log to `.triage/runs/<date>.md`.

`state.json` is the resume point. Never overwrite history, append to
`attempts`. If the file is malformed, stop and spill everything to inbox
rather than risk losing the spine.

### 6. Comments, keep people out of limbo

Voice comes from `.triage/voice.md`. Autonomy tiers (see
`resources/comment-policy.md`):

- **Auto-post: DISABLED** (maintainer directive 2026-07-23). Never post any
  comment or review from the loop, not even low-risk acks.
- **Draft to inbox** (everything): acks, judgments, decisions, promises,
  closures, any reply. Write it under `## Drafts awaiting approval` in
  `inbox.md` with its target, never post it. The maintainer approves, edits,
  or discards each one.

### 7. Spill

Anything the loop could not classify, fix, or safely comment on goes to
`inbox.md` with enough context to act on cold. The inbox is the only thing
the maintainer must read each morning.

### 8. Version bump and publish alert

When a fix PR changes the **published package** (anything under `src/`, or
`package.json` dependencies that ship), bump the version per semver in the same
PR:

- patch (`x.y.Z`) for a bug fix, default for triage fixes.
- minor (`x.Y.0`) only if the fix adds behavior; the loop should not be doing
  these, so if a bump looks bigger than patch, send it to inbox instead.

Do NOT bump for changes that do not ship: lockfile-only updates (e.g. a bare
`npm audit fix`), docs, CI config, tests-only, or anything under `.triage/`.
When unsure whether a change ships, do not bump; note it in the inbox.

**Publishing is always maintainer-triggered.** The loop NEVER runs `npm publish`
or creates a GitHub Release. After a PR that includes a version bump, write a
top-of-inbox alert:

```
## RELEASE NEEDED
- PR #<n> bumps <old> -> <new> (<reason>). After it merges and main is green,
  follow RELEASING.md and create GitHub Release v<new>. The release workflow
  publishes npm with provenance; the loop does not publish.
```

Keep the alert until the GitHub Release, npm package, and installed-package
smoke test are all confirmed.

## Guardrails

- Never push to `main`, never merge, never `--force`. PRs only.
- Never run `npm publish` or create a GitHub Release. Version bumps ride inside
  the fix PR; the maintainer creates the release after merge, flagged via the
  inbox RELEASE NEEDED alert. Follow `RELEASING.md`.
- Never touch files outside the worktree except `.triage/`.
- The token usually lacks the GitHub `workflow` scope, so pushes that change
  `.github/workflows/*` are rejected. Do NOT attempt them; route any CI/workflow
  change to the inbox for the maintainer to apply (or to re-scope the token).
- Respect the per-run finding cap; spill the overflow rather than running long.
- Outward-facing writes: PR create is allowed; comments and reviews are NEVER
  posted by the loop, every one is drafted to the inbox for approval.
- If `gh` is unauthenticated or the tree is dirty, abort and write why to
  `inbox.md`.

## Resources

- `resources/state-schema.md`, state.json shape, id derivation, transitions.
- `resources/finding-rules.md`, worth-doing vs inbox vs ignore, caps.
- `resources/comment-policy.md`, voice bootstrap + autonomy tiers.

© bitbonsai · MIT · bitbonsai/mcpvault

Similar skills

All skills for Agent setup: memory, context, orchestration →

triage by other authors comes first.

triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. CX Codex +1 990,453installs triage official anthropics A skill for Claude Code, Cursor, Codex and other platforms: verifies security scanner reports, deduplicates findings, re-ranks by exploitability, and assigns owners. Runs with /triage on a directory of JSON scanner output. CX Codex +1 1,200installs triage readwiseio triage — a skill for Claude Code and five other platforms that works through your Readwise Reader inbox one document at a time, pitching each item so you can read, save for later, or archive on the spot. CX Codex +1 476installs triage SethGammon triage — a skill for investigating GitHub issues and reviewing PRs. Reads open issues, classifies them, searches the codebase for root cause, proposes fixes with file:line references, and optionally implements them. CX Codex +1 ★ 937repo stars triage TakaGoto The triage skill asks what you’re trying to learn, build, debug, or review in RAG, then points you to a fitting command or agent. Use it when the next step isn’t clear. CX Codex +1 ★ 30repo stars issue-review toss Fetches open GitHub Issues, reads related source code, assigns labels, and groups duplicates. Trigger it with /issue-review from your agent chat. CX Codex +1 208installs triage-issue-reports cursor triage-issue-reports is a Claude Code skill that reviews Slack bug reports, checks evidence, traces causes, and creates tickets only for confirmed new bugs. CX Codex +1 843installs issue-triage davila7 issue-triage triages incoming GitHub and Linear tasks, computes priority scores, and routes issues to matching teams. CX Codex +1 276installs om-auto-merge-triage open-mercato om-auto-merge-triage — a skill for Claude Code that ranks open pull requests for unattended merge queues. It gates candidates across eligibility tiers and labels them only after manual confirmation. CX Codex +1 435installs pr-review-triage Cobus Greyling pr-review-triage tracks open pull requests, checks CI, merge conflicts, stale reviews and unanswered comments, then hands back a ranked list of blockers. CX Codex +1 ★ 11,819repo stars Linear Automation Claude Office Skills Linear Automation automates Linear issue tracking, Git branch and PR syncing, and two-week cycle planning through project-mcp tools. CX Codex +1 4,800installs

From the same set2

Project sponsors

Companies that keep this analytics open