Harness Triage

Triage

Move issues on the project issue tracker through a small state machine of triage roles.

Every comment or issue posted to the issue tracker during triage must start with this disclaimer:

> *This was generated by AI during triage.*

Reference docs

• AGENT-BRIEF.md — how to write durable agent briefs
• OUT-OF-SCOPE.md — how the .out-of-scope/ knowledge base works
• references/effort-calibration.md — token-budget calibration table for Effort field

Roles

Two category roles:

• bug — something is broken
• enhancement — new feature or improvement

Five state roles:

• needs-triage — maintainer needs to evaluate
• needs-info — waiting on reporter for more information
• ready-for-agent — fully specified, ready for an AFK agent
• ready-for-human — needs human implementation
• wontfix — will not be actioned

Every triaged issue should carry exactly one category role and one state role. If state roles conflict, flag it and ask the maintainer before doing anything else.

These are canonical role names — the actual label strings used in the issue tracker may differ. The mapping should have been provided to you - run /setup-harness-skills if not.

State transitions: an unlabeled issue normally goes to needs-triage first; from there it moves to needs-info, ready-for-agent, ready-for-human, or wontfix. needs-info returns to needs-triage once the reporter replies. The maintainer can override at any time — flag transitions that look unusual and ask before proceeding.

Invocation

The maintainer invokes /harness-triage and describes what they want in natural language. Interpret the request and act. Examples:

• "Show me anything that needs my attention"
• "Let's look at #42"
• "Move #42 to ready-for-agent"
• "What's ready for agents to pick up?"

Show what needs attention

Query the issue tracker and present three buckets, oldest first:

1. Unlabeled — never triaged.
2. needs-triage — evaluation in progress.
3. needs-info with reporter activity since the last triage notes — needs re-evaluation.

Show counts and a one-line summary per issue. Let the maintainer pick.

Triage a specific issue

1. Gather context. Read the full issue (body, comments, labels, reporter, dates). Parse any prior triage notes so you don't re-ask resolved questions. Explore the codebase using the project's domain glossary, respecting ADRs in the area. Read .out-of-scope/*.md and surface any prior rejection that resembles this issue.

2. Recommend. Tell the maintainer your category and state recommendation with reasoning, plus a brief codebase summary relevant to the issue. Wait for direction.

3. Reproduce (bugs only). Before any grilling, attempt reproduction: read the reporter's steps, trace the relevant code, run tests or commands. Report what happened — successful repro with code path, failed repro, or insufficient detail (a strong needs-info signal). A confirmed repro makes a much stronger agent brief.

4. Grill (if needed). If the issue needs fleshing out, run a /grill-with-docs session.

5. Apply the outcome:

   • ready-for-agent — post an agent brief comment (AGENT-BRIEF.md).
   • ready-for-human — same structure as an agent brief, but note why it can't be delegated (judgment calls, external access, design decisions, manual testing).
   • needs-info — post triage notes (template below).
   • wontfix (bug) — polite explanation, then close.
   • wontfix (enhancement) — write to .out-of-scope/, link to it from a comment, then close (OUT-OF-SCOPE.md).
   • needs-triage — apply the role. Optional comment if there's partial progress.

Board field sync

Trigger: After the maintainer confirms ready-for-agent or ready-for-human AND the agent brief comment is posted.

Guard: Read .harness/config.json → harness.project_fields. If absent or empty:

⚠️ project_fields not in .harness/config.json — skipping board field sync. Run /setup-harness-skills to populate.

Do not block the triage outcome — continue even if sync is skipped.

Effort-to-Size mapping:

Sequence:

1. Read harness.github.project_v2_id from .harness/config.json — this is the projectId for all mutations.
2. Query repository.issue.projectItems to get the board item ID. If the issue is not yet on the board, call addProjectV2ItemByContentId(projectId, contentId: issueNodeId) to add it and capture the new item ID.
3. Parse Effort integer from the agent brief text (**Effort:** N line).
4. Derive Size from Effort using the mapping above.
5. Ask maintainer for Priority — one question, after brief is confirmed: "Priority? P1 / P2 / P3 / skip" — default skip.
6. Call updateProjectV2ItemFieldValue for Effort (number), Size (singleSelectOptionId), and Priority (if not skipped).
7. Print confirmation: ✅ Board fields updated — Effort: N, Size: X, Priority: Pn (or Priority: not set).

Error handling: If any mutation fails (e.g. token lacks project scope), print ⚠️ Board field update failed: <error> and continue — do not block the triage outcome.

Quick state override

If the maintainer says "move #42 to ready-for-agent", trust them and apply the role directly. Skip grilling entirely. Confirm the mechanical steps first, then ask separately about a brief:

I'll apply `ready-for-agent`, remove `needs-triage`, and post a triage note.
Shall I proceed? Also — would you like me to write an agent brief for this issue?

Do not ask for category, type, or effort fields before the state change. Those belong in a brief, which is optional and separate.

Agent brief template

## Agent Brief

**Category:** bug / enhancement
**Type:** AFK / HITL
**Effort:** N (token budget: 1 = ~150K–200K tokens / single slice; 2 = ~300K–400K / 1 phase; 3 = ~500K–700K / full feature; 4+ = epic)
**Summary:** one-line description of what needs to happen

**Current behavior:**
Describe what happens now. For bugs, this is the broken behavior.
For enhancements, this is the status quo the feature builds on.

**Desired behavior:**
Describe what should happen after the agent's work is complete.
Be specific about edge cases and error conditions.

**Key interfaces:**
- `TypeName` — what needs to change and why
- Config shape — any new configuration options needed

**Acceptance criteria:**
- [ ] Specific, testable criterion 1
- [ ] Specific, testable criterion 2

**Out of scope:**
- Thing that should NOT be changed or addressed in this issue

Use AGENT-BRIEF.md for detailed guidance and examples.

Needs-info template

## Triage Notes

**What we've established so far:**

- point 1
- point 2

**What we still need from you (@reporter):**

- question 1
- question 2

Capture everything resolved during grilling under "established so far" so the work isn't lost. Questions must be specific and actionable, not "please provide more info".

Resuming a previous session

If prior triage notes exist on the issue, read them, check whether the reporter has answered any outstanding questions, and present an updated picture before continuing. Don't re-ask resolved questions.