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.
npx agentmods add skills/datit309/supergraph/triagenpx skills add datit309/supergraph --skill triagegit clone --depth 1 https://github.com/datit309/supergraphWhat 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.
| Model | Per session | Once 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 |
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.
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]"
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.
- 2d ago First seen · 105 lines · 73 tokens per session scan A 732ab1bbfbed
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.
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.
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.
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…
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"…
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…
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…