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 commands/ai-sdlc-framework/ai-sdlc/triagegit clone --depth 1 https://github.com/ai-sdlc-framework/ai-sdlcWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/ai-sdlc-framework/ai-sdlc/triage)<a href="https://agentmods.dev/commands/ai-sdlc-framework/ai-sdlc/triage"><img src="https://agentmods.dev/badge/commands/ai-sdlc-framework/ai-sdlc/triage.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00035 | $0.01855 |
| Opus 5 | $0.00017 | $0.00928 |
| Sonnet 5 | $0.00007 | $0.00371 |
| Haiku 4.5 | $0.00003 | $0.00186 |
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 4d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage issue $ARGUMENTS by running it through @ai-sdlc/orchestrator's
admission composite — the RFC-0008 §A.6 implementation
(P_admission = SA × D-pi_adjusted × ER × (1 + HC) with pillar
breakdown and tension flags). The orchestrator does the math; this
skill's job is to detect the tracker, resolve the right config root,
invoke cli-admit, and present the result with full provenance.
Step 1 — Detect the tracker
Inspect the form of $ARGUMENTS:
- Backlog.md when the id matches
^[A-Za-z][A-Za-z0-9]*-\d+$(e.g.AISDLC-42,task-7,INGEST-101) - GitHub when the id is
\d+or#\d+(e.g.42,#42) - If ambiguous, prefer Backlog when
backlog/tasks/exists in the repo, else GitHub.
Allow override: if $ARGUMENTS contains --tracker github or --tracker backlog, honour that.
Step 2 — Resolve the config root
Cross-repo confusion is the #1 silent failure. Explicitly pin the config root before fetching the issue:
- Backlog: walk up from the task file's directory (or repo cwd) until
.ai-sdlc/is found. That's the config root. - GitHub: walk up from cwd. If
gh pr view's remote URL points at a different repo than the cwd, surface a warning and ask the user to confirm or pass--config-root <path>.
Pass that path through to every cli-admit call as --config-root. The
CLI also auto-walks but explicit pinning eliminates ambiguity in the
report.
Step 3 — Fetch + score
Backlog branch
cli-admit parses the task file directly — no separate fetch step.
Call mcp__backlog__task_view only if you need to render the task
title/body to the user before scoring.
ID=$ARGUMENTS
CONFIG_ROOT=... # from Step 2
pnpm --filter @ai-sdlc/dogfood admit \
--tracker backlog \
--task-id "$ID" \
--config-root "$CONFIG_ROOT" \
--enrich-from-state \
> /tmp/admit.json 2> /tmp/admit-provenance.json
The Backlog adapter does the label/AC/quality-flag mapping internally
(priority:p*, size:[SML], track:*, source:*, Done-with-unchecked-ACs
zombie close, etc.). You don't fan signals out by hand.
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.
- 4d ago First seen · 164 lines · 35 tokens per session scan A 219205984112
triage is a command published in the GitHub repository ai-sdlc-framework/ai-sdlc (100 stars, last pushed 10d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,855 once invoked, about $0.0002 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 commands, from other repositories
remediate
Close the debt the deterministic lanes cannot version-bump away: the grandfathered broken build, advisories with no direct upgrade path, the lint backlog, missing tests, missing docs. Each run plans that debt as finite work orders and works them in two tiers: deterministic recipes execute first at $0 (lockfile resync…
work
Complete reference for work refine, work review, work pause, and work resume commands.
project
Complete reference for all project-related commands — init, show, and update.
metrics
Read-only 3-metric governance glance — override rate, small-lane rate, sprint low-confidence ratio — each with a trend arrow vs. the prior 20-commit window.
audit
Assemble the governance record for a range — commits, overrides, ADRs, sprint auto-decisions, open questions, checkpoint findings — into one dated audit packet. Read-only.
sprint
Autonomous sprint — one interactive spec gate, then plan-to-PR execution with every auto-decision SMARTS-scored and logged. Hard gates remain true stops.