Borrowing it
Nothing to install: this file belongs to DantesPeak85/the-council. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DantesPeak85/the-council/main/CLAUDE.mdgit clone --depth 1 https://github.com/DantesPeak85/the-councilWrote 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/instructions/dantespeak85/the-council/claude-md)<a href="https://agentmods.dev/instructions/dantespeak85/the-council/claude-md"><img src="https://agentmods.dev/badge/instructions/dantespeak85/the-council/claude-md/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/instructions/dantespeak85/the-council/claude-md"><img src="https://agentmods.dev/badge/instructions/dantespeak85/the-council/claude-md.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 | $0.01433 | $0.01433 |
| Opus 5 | $0.00717 | $0.00717 |
| Sonnet 5 | $0.00287 | $0.00287 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade B, and why
the-council CLAUDE.md scanned grade B 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 today.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `CODEX_MODEL` | unset → `~/.codex/config.toml` | Codex advisor model (passed via `-m`) | This is a copy
97% identical to the-council AGENTS.md — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
The Council is a Claude Code Skill plugin that convenes Qwen through OpenRouter and Google Gemini as its default advisory board. Codex remains available as an explicit seat or compatibility fallback. The advisors return independent analyses that Claude synthesizes into unified recommendations.
This is not a Node/TypeScript application — it's a pure Bash + Markdown skill with no build system, package manager, or test framework.
Architecture
skills/the-council/
├── SKILL.md # Operational guide (skill definition + workflow)
├── references/prompt-templates.md # 4 prompt templates (review, architecture, debug, general)
└── scripts/
├── council_preflight.sh # Detects available CLIs + auth status (cached 2h)
├── council_sync.sh # Read-only shim; legacy interrupted-run recovery only
└── council_invoke.sh # Parallel CLI invocation: timeouts, OS sandbox, snapshot safety net, response validation
Execution flow: Preflight → Compose an inlined prompt → Invoke advisors in parallel → Synthesize responses → Generalize learnings. The project's AGENTS.md is never replaced.
Operating modes are determined by preflight: Qwen + Gemini by default, Qwen-only, Gemini-only, explicit Codex modes, or a loudly announced Codex compatibility fallback when OpenRouter is unavailable.
Key Design Decisions
- Read-only enforcement (1.3.0+): Both advisors run with OS-level deny-write sandboxes on macOS. Codex uses its built-in
--sandbox read-only. Gemini (agy) is wrapped insandbox-execwith a deny-write profile atskills/the-council/scripts/council_sandbox.sb; writes are allowed only to~/.gemini/, the per-invocation.council-tmp/<...>/dir, system temp, and agy-specific~/Library/Caches/subdirs. On non-macOS, the script refuses to run agy unless--allow-unsandboxed-geminiis passed. - Diff safety net (1.3.0+): pre/post-invocation snapshot of
$WORK_DIR(git: HEAD + status with--ignored=traditional+ sha256 of tracked + untracked + gitignored files; non-git: find + sha256). Snapshot excludes.council-tmp/(response files) and.antigravitycli/(agy's housekeeping dir). Any other change fails the invocation with exit 2 and a[COUNCIL_SAFETY_NET]banner. See SKILL.md for the historical 1.2.x ghost-write incident this replaces. - Gemini invocation (1.4.0): Gemini reviews the INLINED prompt only — no project
--add-dir, no repo exploration. The composed prompt is written into the per-invocation.council-tmp/<run>/dir, which becomes the advisor's only workspace. The backend is resolved at runtime:geminiCLI (single-shot, stdin, JSON envelope) when a paidGEMINI_API_KEY/GOOGLE_API_KEYis set andgeminiis on PATH, elseagy(pty-wrapped viascript, sandboxed). The oldmaxSessionTurnssettings injection was a verified no-op and is gone —~/.gemini/antigravity-cli/settings.jsonis never touched. - Prompt sanitization:
jsr:import strings are redacted from the Gemini prompt before invocation to avoid spurious safety/policy blocks fromagy. - Empty-response retry: If
agyexits 0 with no stdout and no stderr, the invocation is retried once before being reported as failed. - Response validation (1.4.0): an advisor fails only on empty output, a script-written
[COUNCIL-ADVISOR-FAILURE]placeholder, a nonzero exit with no verdict line, a refusal, or non-engagement (a short verdict-less reply to a large prompt). The old response-body word-grep (policy/blocked/quota/rate limit) is gone — it false-failed substantive reviews; stderr noise now demotes to an advisory*_warnings.log, not a failure. - Parallel execution: Both advisors run as background processes with configurable timeout (
COUNCIL_TIMEOUT, default 600s). - NVM compatibility:
council_invoke.shloads NVM environment to find globally-installed CLI tools. - macOS support: Uses
gtimeout(from coreutils) when available, falls back totimeoutor no timeout. - Graceful degradation: Works with one advisor if the other is unavailable; shows install help if neither exists.
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.
- today Changed · -162 tokens per session scan D → B 24b2a5a7b775
- 10d ago First seen · 59 lines · 1,595 tokens per session scan D 06951f0e48e6
the-council CLAUDE.md is an instructions file published in the GitHub repository DantesPeak85/the-council (3 stars, last pushed today), licensed MIT. It adds 1,433 tokens to every session, about $0.0072 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 97% identical to the-council AGENTS.md, differing in 8 lines, and is treated as a copy.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.