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 sananthanarayan/skilldrop --skill council-reviewgit clone --depth 1 https://github.com/sananthanarayan/skilldropWrote 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/sananthanarayan/skilldrop/council-review)<a href="https://agentmods.dev/skills/sananthanarayan/skilldrop/council-review"><img src="https://agentmods.dev/badge/skills/sananthanarayan/skilldrop/council-review/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/sananthanarayan/skilldrop/council-review"><img src="https://agentmods.dev/badge/skills/sananthanarayan/skilldrop/council-review.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 | $0.00138 | $0.02384 |
| Opus 5 | $0.00069 | $0.01192 |
| Sonnet 5 | $0.00028 | $0.00477 |
| Haiku 4.5 | $0.00014 | $0.00238 |
Grade A, and why
council-review 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 10d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
council-review
You convene a council of distinct expert personas to deliberate something consequential, then reconcile their views into a decision. The value is not five voices agreeing — it's surfacing where senior engineers genuinely disagree, naming the tradeoff at the heart of it, and deciding anyway.
This is the deliberation counterpart to the single-voice reviewers. Use devils-advocate when you want one adversarial pass on code, doc-critique for one pass on a doc, tech-comparison-matrix for a weighted scoring of named options. Use the council when the question is open, the tradeoffs are real, and you need multiple disciplines in the room.
What the council reviews
Three shapes — the seats apply to all three; their evidence just differs:
| Shape | Example | Evidence a seat cites |
|---|---|---|
| Decision / question | "Monolith or services?" · "Adopt Kafka?" · "Rewrite or refactor?" | the specific claim or assumption |
| Design / RFC | a design doc, an architecture proposal, an API contract | the section / interface |
| Code change | a diff, a PR, a load-bearing module before merge | file:line |
If the scope is unclear, ask once which of the three it is. Don't convene a council on the whole repo — the scope is the decision/design/change in front of you.
The council
Five standing seats — each a distinct mandate with a lane it stays in. Read the seat file before speaking for it:
| Seat | Asks | File |
|---|---|---|
| 🏛 Architect | Does this fit the system? Right abstraction, coupling, long-term complexity? | seats/architect.md |
| 🔒 Security Engineer | What's the threat model? Trust boundaries, data, dependencies? | seats/security-engineer.md |
| 🛠 Operator (SRE) | What happens at 3am? Failure modes, rollback, observability, blast radius? | seats/operator.md |
| ⚖️ Pragmatist | Is this the simplest thing that works? Over-engineered? Do we even need it? | seats/pragmatist.md |
| 👤 User-Advocate | Is it correct for the people who use it? Edge cases, errors, contracts, compat? | seats/user-advocate.md |
What ships with it
12 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.
- evals/eval_queries.json 987 B
- evals/evals.json 1.1 KB
- examples/redis-cache-decision.md 6.2 KB
- manifest.json 1.2 KB
- reference.md 5.8 KB
- seats/architect.md 2.4 KB
- seats/bench.md 3.8 KB
- seats/operator.md 2.4 KB
- seats/pragmatist.md 2.7 KB
- seats/security-engineer.md 2.5 KB
- seats/user-advocate.md 2.8 KB
- templates/council-review.md 2.3 KB
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.
- 10d ago First seen · 107 lines · 0 tokens per session scan A 6a750b67ef36
council-review is a skill published in the GitHub repository sananthanarayan/skilldrop (2 stars, last pushed 26d ago), licensed MIT. It adds 138 tokens to every session and 2,384 once invoked, about $0.0007 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
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".