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 richfrem/agent-plugins-skills --skill copilot-cli-agentgit clone --depth 1 https://github.com/richfrem/agent-plugins-skillsWrote 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/richfrem/agent-plugins-skills/copilot-cli-agent)<a href="https://agentmods.dev/skills/richfrem/agent-plugins-skills/copilot-cli-agent"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/copilot-cli-agent/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/richfrem/agent-plugins-skills/copilot-cli-agent"><img src="https://agentmods.dev/badge/skills/richfrem/agent-plugins-skills/copilot-cli-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00685 |
| Opus 5.5 | $0.00015 | $0.00274 |
| Sonnet 5.5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
copilot-cli-agent 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 18d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot CLI Agent
Dispatch the authorized task using the bundled router.
Contents
Constraints
Reuse the user's runtime/model/effort choice; do not start an unrequested review.
Use one backend; halt on failure without silent fallback. Analysis uses --isolated;
it suppresses dangerous flags and adds instructions, but is not an OS sandbox.
Non-isolated dispatch requires authorization and external containment where needed.
Quick start
Run from this skill root; input and output paths are supplied by the caller:
python3 scripts/run_agent.py agents/security-auditor.md <input> <output> "Review supplied source." --cli copilot --isolated --require-input
Workflow
- Read dispatch details before selecting flags or models.
- Read execution rules and backend capabilities; user instructions govern authorization.
- Use the selected model or catalog tier; inspect the resolved executable/version.
- Dispatch once, then check exit status, nonempty output and requested acceptance criteria.
Profile contract applies when a caller supplies a profile.
Verification
Record backend, executable/version, model, effort, scope and result. Empty or failed
output is not a completed review. Log failures in Map Debt.
For gated reviews, wrap supplied input in ---SOURCE--- blocks and record results through the control-plane record-critic-review command using canonical PASS, REVISE, or REJECT; only PASS approves.
🎭 Persona Registry (agents/)
These personas are mirrored across CLI agent dispatchers to ensure consistent analytical behavior across the ecosystem.
What ships with it
36 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/architect-review.md 35 B
- agents/refactor-expert.md 34 B
- agents/security-auditor.md 35 B
- evals/.lock.hashes 420 B
- evals/evals.json 1.2 KB
- evals/experiments/2026-03-13_182514/results.json 35 KB
- evals/experiments/2026-03-13_182514/results.tsv 10 KB
- evals/experiments/2026-03-13_182514/timing.json 1.8 KB
- evals/experiments/2026-03-13_183006/results.json 3.0 KB
- evals/experiments/2026-03-13_183006/results.tsv 327 B
- evals/experiments/2026-03-13_183006/timing.json 273 B
- evals/experiments/2026-03-13_183028/results.json 5.6 KB
- evals/experiments/2026-03-13_183028/results.tsv 1.5 KB
- evals/experiments/2026-03-13_183028/timing.json 453 B
- evals/experiments/2026-03-13_183345/logs/improve_iter_1.json 9.6 KB
- evals/experiments/2026-03-13_183345/results.json 5.3 KB
- evals/experiments/2026-03-13_183345/results.tsv 778 B
- evals/experiments/2026-03-13_183345/timing.json 453 B
- evals/results.tsv 293 B
- examples/output_restored.md 666 B
- examples/output.md 329 B
- examples/target.py 292 B runs code
- references/acceptance-criteria.md 60 B
- references/backend-capabilities.md 43 B
- references/capability-profile-contract.md 50 B
- references/cheapest_models.json 40 B
- references/cheapest_models.md 38 B
- references/copilot-cli-dispatch.md 43 B
- references/copilot-models.json 39 B
- references/execution-contract.md 41 B
- references/fallback-tree.md 54 B
- references/map-debt.md 31 B
- references/program.md 30 B
- scripts/capability_profile.py 38 B runs code
- scripts/model_catalog.py 33 B runs code
- scripts/run_agent.py 29 B runs code
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.
- 18d ago Changed · -234 lines · -16 tokens per session c51e51dfdb85
- 1mo ago Changed · +15 lines 995e73c85dfd
- 1mo ago Changed · -36 lines 9752b53b393f
- 1mo ago Changed · +20 lines 2d35c7f3425a
- 1mo ago Changed · +7 lines 673606eff935
- 1mo ago First seen · 301 lines · 53 tokens per session scan A 36011ca194e7
copilot-cli-agent is a skill published in the GitHub repository richfrem/agent-plugins-skills (7 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 685 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
autoprompt
Run explicitly requested Autoprompt v2 work through the private controller. Ordinary coding and review requests do not activate this skill.
ap-route-analyst
Inspect only enough read-only project information to recommend a route and list the facts behind that recommendation.
ap-roadmap-author
Write one dependency-ordered roadmap with owners, integration points, success items, and real checks.
ap-depth-prober
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-fresh-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.