triage

A process for classifying issues as bugs, enhancements, questions, or research tasks, then assigning each a clear state. An issue is a reported problem, request, or question about a software project.

In plain words
What is it for?
Use it to review a backlog, request missing details, decide whether work is ready for an agent, or route issues that require human judgment.
Why use it?
It prevents unclear or incomplete issues from entering development without the information or human decisions they need.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/datit309/supergraph/triage
Any agent
npx skills add datit309/supergraph --skill triage
Clone the repo
git clone --depth 1 https://github.com/datit309/supergraph

Made for: Claude Code, Codex.

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 853 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.00853
Opus 5 $0.00036 $0.00426
Sonnet 5 $0.00015 $0.00171
Haiku 4.5 $0.00007 $0.00085

Measured 2d ago against content hash 732ab1bbfbed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/supergraph/skills/triage/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/supergraph:triage

Classify issues with a formal state machine. ready-for-agent is the handoff trigger to the supergraph pipeline.

Announce: "🗂️ /supergraph:triage — classifying issues..."

State Machine

needs-triage
    ├── enough info → [assign category] → ready-for-agent | ready-for-human
    └── missing info → needs-info → [info provided] → ready-for-agent | ready-for-human

ready-for-agent  → supergraph:plan pipeline
ready-for-human  → manual dev / architectural decision needed
wontfix          → closed with reason

Category Roles

Category When
bug Observed behavior differs from specified behavior
enhancement New capability or improvement to existing behavior
question Needs clarification before any action
spike Research / proof-of-concept, no production code

State Roles

State Meaning
needs-triage Unreviewed — default for new issues
needs-info Blocked on missing information from reporter
ready-for-agent Fully specified — safe for /supergraph:plan to consume
ready-for-human Needs human judgment (architecture, business decision, security)
wontfix Will not be addressed — reason required

Triage Workflow

For each issue:

1. Read the issue completely.

2. Assign category — bug / enhancement / question / spike.

3. Check readiness for agent:

A bug is ready-for-agent when:

  • Steps to reproduce are clear
  • Expected vs actual behavior is stated
  • Environment info is present (version, OS, config)
  • No architectural decision required

An enhancement is ready-for-agent when:

  • Acceptance criteria are defined
  • Scope is bounded (not open-ended)
  • No design decision blocking implementation

If NOT ready → set needs-info and list exactly what's missing (one question per response).

4. Assign state and apply labels via GitHub CLI:

gh issue edit <number> --add-label "bug,needs-info"
gh issue edit <number> --add-label "enhancement,ready-for-agent"
gh issue edit <number> --add-label "wontfix"
# Add comment explaining state change:
gh issue comment <number> --body "Triage: [reason for state]"

Read the full file on GitHub · 105 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 105 lines · 73 tokens per session scan A 732ab1bbfbed

Subscribe to this mod's changes

triage is a skill published in the GitHub repository datit309/supergraph (21 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 853 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

now-what

Recommend what to do next for current work by inspecting available work signals. Do not use for handoff files, implementation planning, status reports, or broad backlog triage.

hon454/grimoire · 38 tokens

ambient-project

Quietly maintain a useful project view from meaningful work in the current Codex session. Use when work creates a task, bug, decision, idea, risk, milestone, plan, progress update, or explicit completion.

Bene-2020/plane-codex-mcp · 46 tokens

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens

user-story-generator

Transforms requirements into user stories with Given/When/Then acceptance criteria ready for sprint planning and Jira. Use when user needs to write user stories, create Jira tickets, define acceptance criteria, or says "user stories", "acceptance criteria", "sprint backlog", "Jira tickets", "as a user I want"…

lenar-amirov/product-pipeline-public · 76 tokens

migrate

Inventory an existing spec-driven project and apply bounded migrations to jig defaults: report, adopt-layout, rename-decisions, split-slices, slice-to-spec, seed-decisions, and copy-machinery. Use when the user says migrate this project to jig, adopt jig here, this repo already has specs — set up jig, scaffold-init…

ramboz/jig · 151 tokens

adr-workflow

Scaffold, accept, index, and link Architectural Decision Records (ADRs). Use when the user says "write an ADR", "record this decision", "resolve [deferred item] with an ADR", "supersede ADR-NNNN", or otherwise wants to capture a hard-to-reverse decision in docs/decisions/. Also use when a refinement-todo entry needs…

ramboz/jig · 122 tokens