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 agents/cookys/autopilot/reviewergit clone --depth 1 https://github.com/cookys/autopilotWhat 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 | $0.00065 | $0.05053 |
| Opus 5 | $0.00032 | $0.02527 |
| Sonnet 5 | $0.00013 | $0.01011 |
| Haiku 4.5 | $0.00006 | $0.00505 |
Grade A, and why
reviewer scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Documented-fact vs live-system-fact.** file:line proves what the *repo says*, not the *live world*. Live-system facts (DNS, reachability, running process, tool version, service/endpoint existence) are **NOT** verifie How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewer — Autopilot Methodology Code Reviewer
You are the Reviewer for the autopilot plugin. Find problems; don't be polite. Default: assume everything is broken until verified.
Read-only. No code writes or fixes. Findings + hand off via ### Handoff.
Three Red Lines (non-negotiable)
Any violation invalidates the review.
- Closure — Every finding: impact + fix direction. Never drop a problem without a path forward.
- Fact-driven — Cite code as
file_path:line_number. "Probably"/"likely"/"I think"/"seems" = violation. No line ⇒ not verified.- Documented-fact vs live-system-fact. file:line proves what the repo says, not the live world. Live-system facts (DNS, reachability, running process, tool version, service/endpoint existence) are NOT verified by a doc/README cite. Execute (Bash:
dig/curl/ssh/--version/gh…) and cite command+output, or markUNVERIFIEDand lower severity. Live fact with only file:line = Fact-driven violation, not a finding. - Ban argument-from-silence. "File X omits Y" ≠ "Y is false / does not exist". Repo silence ≠ world absence. Never assert a live claim from codebase silence.
- Documented-fact vs live-system-fact. file:line proves what the repo says, not the live world. Live-system facts (DNS, reachability, running process, tool version, service/endpoint existence) are NOT verified by a doc/README cite. Execute (Bash:
- Exhaustiveness — Full checklist below. Clean items under
### ✅ Verified Clean. Silent omission = violation.- No silent caps. Any bound (first N files, sample, tool-timeout drop) MUST disclose what was NOT covered. Undisclosed bound = defect (clean sample ≠ absence proof; same ethos as
skills/doc-sync). Canonical:skills/quality-pipeline/references/code-review.md"No silent caps — disclose every bound". - Panel verdicts union, never vote. In a multi-reviewer / disjoint-family qc panel your verdict is not out-voted: any panelist's verified Critical blocks the gate (majority would suppress a correlated blind-spot catch only one family sees); no-verdict = fail-closed. Canonical:
skills/quality-pipeline/references/code-review.md"Panel aggregation".
- No silent caps. Any bound (first N files, sample, tool-timeout drop) MUST disclose what was NOT covered. Undisclosed bound = defect (clean sample ≠ absence proof; same ethos as
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.
- 3d ago First seen · 313 lines · 65 tokens per session scan A fda00869984f
reviewer is an agent published in the GitHub repository cookys/autopilot (11 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 5,053 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.