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 alinaqi/maggy --skill council-reviewgit clone --depth 1 https://github.com/alinaqi/maggyWrote 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/alinaqi/maggy/council-review)<a href="https://agentmods.dev/skills/alinaqi/maggy/council-review"><img src="https://agentmods.dev/badge/skills/alinaqi/maggy/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/alinaqi/maggy/council-review"><img src="https://agentmods.dev/badge/skills/alinaqi/maggy/council-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Rogue Agent · line 4 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 59 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00028 | $0.00766 |
| Opus 5 | $0.00014 | $0.00383 |
| Sonnet 5 | $0.00006 | $0.00153 |
| Haiku 4.5 | $0.00003 | $0.00077 |
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 13d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council of Experts — Multi-Model Validation
When to Auto-Trigger
Plans (auto_validate_plans)
When you write a plan to ~/.claude/plans/, automatically validate it:
~/bin/validate-plan --threshold 2 ~/.claude/plans/<plan-file>.md
- 2+ of 3 approve → execute immediately
- 1 of 3 → surface reviewer feedback to user before proceeding
- 0 of 3 → revise plan, re-validate
Architecture Decisions (auto_review_architecture)
When making architectural changes (new services, API redesigns, database schema changes), run:
~/bin/review --all "Review this architecture: <summary>"
PR Review (auto_review_prs)
Before marking a PR as done, run:
~/bin/review --all --file <changed-files>
Configuration
Council behavior is configured in ~/.claude/council.yaml. The Maggy dashboard (Settings > Council) also manages this config.
Chief of the Council
chief: claude-fable-5 — Claude Fable 5 (Anthropic's most capable widely-released
model, GA 2026-06-09) leads every panel as the chief: it reviews first and casts
the deciding synthesis. Invoked via ~/bin/claude-fable-5. Override the chief in
~/.claude/council.yaml.
Reviewer Contexts
The chief leads each context, followed by the panel:
| Context | Default Reviewers | When |
|---|---|---|
plan |
Claude Fable 5 (chief), DeepSeek Pro, Codex, Gemini Pro | Before executing any plan |
review |
Claude Fable 5 (chief), DeepSeek Pro, Kimi | Code review, PR review |
architecture |
Claude Fable 5 (chief), DeepSeek Pro, Gemini Pro, Grok | System design, schema changes |
Threshold Rules
The threshold setting controls how many approvals are needed:
threshold: 2with 3 reviewers → need 2/3 to auto-execute- Clamped to [1, reviewer_count] — can't be 0 or exceed available reviewers
Model Inventory
All 13 tiers are listed in ~/.claude/council.yaml under models:. Each has:
id— unique identifiercmd— CLI command to invoke (null for Claude models, which are the host)tier— routing priority (0=cheapest, 12=most capable)label— human-readable name
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.
- 13d ago First seen · 77 lines · 28 tokens per session scan A 326af45ba7dc
council-review is a skill published in the GitHub repository alinaqi/maggy (707 stars, last pushed 4d ago), licensed MIT. It adds 28 tokens to every session and 766 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 2026-08-30.
Other skills, from other repositories
ring:adopting-lib-commons-huma-wrapper
Adopting the lib-commons/v5 shared Huma (OAS 3.1) OpenAPI wrapper + RFC 9457 problem model (commons/net/http/{openapi,problem}) in a Lerian Go service: wire openapi.New/ServeSpec + problem.Install (central >=500 scrub) on BOTH runtime and spec-gen paths, the per-rail problem.MapError flex seam, and rename-only spec…
culture
Primarily the agent's internal-thinking skill — invoke it silently to model a problem, identify trade-offs, and decide what to do, BEFORE asking the user anything or dispatching another skill. Only treat this as a user-facing skill when the user has explicitly opted out of code writes — phrases like "no writes", "just…
ring:engineering-prompts
Expert prompt engineering and optimization for LLMs and AI systems. Covers core patterns (zero-shot, few-shot, CoT, role-playing, constitutional, tree-of-thoughts), common use cases, and a three-phase process. Use when crafting or optimizing prompts for AI systems. Skip when the prompt is trivial or already performing…
writing-python
Idiomatic Python 3.12+ development. Use when writing Python code, CLI tools, scripts, or services. Emphasizes stdlib, type hints, fast pytest feedback, uv/ruff/pyright toolchain, and minimal dependencies. NOT for Go, Rust, TypeScript, or shell-only tasks.
python-authoring
Write, edit, refactor, or review Python in easy-cheese with concise stdlib-first code, Python 3.12, Shiv .pyz packaging, and repository test and validation conventions. Use for Python changes under src/, scripts/, .github/scripts/, or tests/, especially when the user asks for Pythonic, succinct, de-slopped…
agent-mle-reviewer
Production machine-learning engineering reviewer for data contracts, feature pipelines, training reproducibility, offline/online evaluation, model serving, monitoring, and rollback. Use when ML, MLOps, model training, inference, feature store, or evaluation code changes.