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 skills add arcasilesgroup/ai-engineering --skill ai-github-triagegit clone --depth 1 https://github.com/arcasilesgroup/ai-engineeringWrote 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/skills/arcasilesgroup/ai-engineering/ai-github-triage)<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-github-triage"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-github-triage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arcasilesgroup/ai-engineering/ai-github-triage"><img src="https://agentmods.dev/badge/skills/arcasilesgroup/ai-engineering/ai-github-triage.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00165 | $0.05083 |
| Opus 5.5 | $0.00066 | $0.02033 |
| Sonnet 5.5 | $0.00033 | $0.01017 |
| Haiku 4.5 | $0.00016 | $0.00508 |
Grade A, and why
ai-github-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 11d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-github-triage — read the backlog, rank it, touch nothing
One page that answers "what should we work on next", built from every open issue and pull request, with each claim pinned to the line of code that proves it. The output is a decision surface: a ranked queue at the top, the evidence behind it below, the commands to start at the end. Nothing this skill does reaches GitHub.
What it produces
One file, .ai-engineering/triage.html, rewritten in place by every run of the same
repository. It is a slot, not a numbered folder: the page is the backlog's current state,
and git keeps what the last run said.
The absolute rule: read-only
The page is the only artifact. Every mutation of GitHub state is a failure of this skill, not a shortcut in it.
| Forbidden | Allowed |
|---|---|
gh issue comment, gh issue close, gh issue edit |
gh issue view, gh issue list |
gh pr comment, gh pr merge, gh pr review, gh pr edit, gh pr checkout |
gh pr view, gh pr list, gh pr diff |
gh api -X POST, -X PUT, -X PATCH, -X DELETE |
gh api without a method (GET) |
git checkout, git switch, git fetch, git pull on a branch under review |
git log, git show, git blame, git rev-parse |
| Labeling, assigning, reopening, transferring | Reading the tree, the diff and the history |
No subagent gets a verb from the left column. A PR row says MERGE or BLOCKED; a human
merges. The single tempting exception, "just close the duplicate", is the rule's own
example of a violation.
Which repository (the scope rule, decided before anything else)
- No URL — the current repository:
gh repo view --json nameWithOwner -q .nameWithOwner. If the directory is not a git repository orghhas no repo, say which of the two failed and stop. - A URL,
owner/repo, or a path to another checkout — that backlog:https://github.com/owner/repo/issues,https://github.com/owner/repo/pulls, the bare slug, or a directory that has a remote. - One run, one repository. Never merge two backlogs into one page, even when the same
project owns both. State the target on the page (
ai-triage-repo) so the next run knows which backlog this was.
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.
- 11d ago First seen · 329 lines · 165 tokens per session scan A 8b8e7923fe14
ai-github-triage is a skill published in the GitHub repository arcasilesgroup/ai-engineering (61 stars, last pushed 2d ago), licensed Apache-2.0. It adds 165 tokens to every session and 5,083 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-10-05.
Other skills, from other repositories
spec-kitty-implement-review
Orchestrate the implement-review loop for Spec Kitty work packages using any configured agent. Covers agent dispatch, state transitions, rejection cycles, arbiter escalation, and dependency-aware sequencing across all 13 supported coding agents. Triggers: "implement and review WPs", "run the implement-review loop"…
spec-kitty-runtime-review
Review runtime-owned outputs using the Spec Kitty review workflow surface, then direct approval or rejection with structured feedback. Triggers: "review this work package", "check runtime output", "approve this step", "review WP", "is this WP ready to approve", "check this implementation". Does NOT handle: setup-only…
planner
Script-guided plan-and-execute workflow run one numbered step at a time. planner.py drafts a plan through forced reflection pauses, then runs a technical-writer and quality-reviewer review of the plan file; executor.py delegates each milestone of an approved plan file to specialized agents and, on resume, reconciles…
execution-plans
Manage execution plans as versioned artifacts with progress tracking and decision logs. Use when you say "create execution plan", "update plan progress", "log decision", "complete plan", or "abandon plan". Do NOT use to break work into milestones (use plan) or to execute an approved plan file through delegation (use…
work-operating-model
Run a 5-layer interview to elicit how a team actually works (rhythms, decisions, dependencies, institutional knowledge, friction) and emit a structured operating model. Use when you say "elicit operating model", "interview team operating model", "how does this team actually work", or "validate operating model". Do NOT…
retro
Fill an unfilled auto-retrospective skeleton for a date, or list the skeletons still pending. Use when you say retro fill, fill retro skeleton, or list pending retros. Do NOT use to run the retrospective analysis itself (this hands off to the retrospective skill), and do NOT use to write a session log.