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 chf3198/copilot-governance --skill role-consultant-critiquegit clone --depth 1 https://github.com/chf3198/copilot-governanceWrote 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/chf3198/copilot-governance/role-consultant-critique)<a href="https://agentmods.dev/skills/chf3198/copilot-governance/role-consultant-critique"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/role-consultant-critique/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/chf3198/copilot-governance/role-consultant-critique"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/role-consultant-critique.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 | $0.00026 | $0.01109 |
| Opus 5 | $0.00013 | $0.00554 |
| Sonnet 5 | $0.00005 | $0.00222 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
role-consultant-critique 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Consultant Critique
Comprehensive Check Registry
Run node scripts/global/consultant-checks.js --issue <N> --json > /tmp/checks.json before CLOSEOUT.
Checks span 3 domains: governance (baton artifacts, labels, events), tools (wiki growth, skill refs), fleet (device routing, cost budget).
Include checks_run: <N>/<total> and checks_failed: <N> in CLOSEOUT output.
Responsibilities
- Perform independent quality/risk review of ALL prior roles.
- Score confidence and identify residual risk.
- Grade Manager scope quality — were gates testable and complete?
- Grade Collaborator implementation — evidence per gate, no gold-plating?
- Grade Admin process — clean deployment, proper git hygiene?
- Audit ticket governance, wiki generation, and fleet routing.
- Recommend follow-up actions with priority.
- Identify at least one concrete improvement per role per review.
Grading rubric
For G1-G9 harness goal scores, use the deterministic v2 rubric. Run
node scripts/global/rubric-score.js --trail <issue-trail> --diff <pr.diff> --closeout <closeout-draft> and paste only its JSON under
### Deterministic Rubric. Subjective scoring text belongs in
### Rationale and must not affect boxes_checked, boxes_total, score, or
mean. Legacy G1=9, G2=8, ... scoring remains accepted only through the
2026-05-22 transition window.
| Area | Pass | Fail |
|---|---|---|
| Scope testability | All gates have binary pass/fail | Vague gates ("make it good") |
| Evidence completeness | Each gate has artifact | Missing gate results |
| Process adherence | Branch, commit, PR, merge per protocol | Skipped steps |
| Ticket governance | Issue exists, linked, labeled | No issue, orphan commits |
| Comment protocol | Each role posted structured comment | Missing role comments |
| Wiki growth | Research → wiki pages generated | Research with 0 wiki pages |
| Fleet routing | Tasks use appropriate devices | All tasks on one device |
Ticket baton protocol (CLOSEOUT)
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 · 101 lines · 26 tokens per session scan A ac2ca5dc4860
role-consultant-critique is a skill published in the GitHub repository chf3198/copilot-governance (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 1,109 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
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…