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 Lee-W/maigo --skill strict-triagegit clone --depth 1 https://github.com/Lee-W/maigoWrote 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/lee-w/maigo/strict-triage)<a href="https://agentmods.dev/skills/lee-w/maigo/strict-triage"><img src="https://agentmods.dev/badge/skills/lee-w/maigo/strict-triage.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 170 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00074 | $0.02309 |
| Opus 5 | $0.00037 | $0.01154 |
| Sonnet 5 | $0.00015 | $0.00462 |
| Haiku 4.5 | $0.00007 | $0.00231 |
Grade A, and why
strict-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 8d 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Strict Triage
Owner Agent: Soyo (Reviewer)
Consumers: /maigo:triage-issue step 3
Core stance: default NEEDS_INFO
Verdict starts at NEEDS_INFO. Maintainer time is the scarce resource. An issue with missing info or unclear scope wastes the next contributor who picks it up. "Looks reasonable at a glance" must not become "wasted three contributors before we realized scope was wrong" — the checklist is the guardrail.
These do not count as enough to upgrade to READY:
- "感覺像是 bug 吧" — without repro steps, you can't tell
- "之前有人問過類似的" — without the prior issue # linked, the next contributor will re-investigate
- "我猜作者意思是 X" — issue body is the source of truth; if it's ambiguous, ask
The 9-item triage checklist
Every triage must walk through every item. Output explicitly marks [x] or [ ] per item.
- Specific title — Title points at a concrete behaviour or feature, not "doesn't work" / "請新增功能" / "壞了"
- Repro steps (bug only) — If classified as bug: numbered or bulleted steps a maintainer can run. Skip with
[—]if not bug. - Expected vs actual (bug only) — Both sides stated; "it crashes" without "what should have happened instead" doesn't count. Skip with
[—]if not bug. - Environment info (bug only) — Version / OS / runtime / relevant config. Skip with
[—]if not bug. - No obvious duplicate — Raana's grep / linked-issue scan did not surface a same-bug / same-request issue. If one was found, must reference its
#N. - In project scope — Belongs in this repo, not an upstream dep / unrelated tool / fork-only concern.
- Has actionable next step — A maintainer could write a 1-line response that moves it forward (ask X, label as Y, assign to Z, close as W). "Interesting thought" with no path forward fails this.
- Follows issue template — If
.github/ISSUE_TEMPLATE/exists in the repo, the relevant sections are filled. Missing template →[ ]and call out which sections are blank. - Signal not buried — Discussion / "+1" / "me too" comments do not overwhelm the original report. If they do, summarise the core in your draft response so future readers don't have to dig.
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.
- 8d ago First seen · 173 lines · 74 tokens per session scan A d303fb58631b
strict-triage is a skill published in the GitHub repository Lee-W/maigo (14 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 2,309 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…