agentmods.dev

councilof-ai: Instructions file for Claude Code

CLAUDE.md

councilof-ai CLAUDE.md is an instructions file for Claude Code from CSOAI-ORG/councilof-ai. It costs 1,593 tokens per session, scanned B, original, MIT.

Repository instructions for coordinating AI-agent work on the Council of AI project. They record deployment facts, build locations, release checks, and project-specific rules.

In plain words
What is it for?
Use them when building, reviewing, or deploying the project, especially when checking the correct client directory, deployment target, and live-site verification steps.
Why use it?
They keep agents aligned with the current deployed setup and the project’s source of truth. This helps avoid using obsolete folders, services, or deployment procedures.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is CSOAI-ORG/councilof-ai's own configuration. It tells Claude Code how to work on councilof-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything councilof-ai configures →

not rated 0repo changed 3d ago B scan 1,593 tokens original MIT
View source ↗ CSOAI-ORG/councilof-ai councilof.ai
Reuse

Borrowing it

Nothing to install: this file belongs to CSOAI-ORG/councilof-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CSOAI-ORG/councilof-ai/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/CSOAI-ORG/councilof-ai

Made for: Claude Code.

Wrote 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.

agentmods badge for councilof-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/csoai-org/councilof-ai/claude-md/github.svg)](https://agentmods.dev/instructions/csoai-org/councilof-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/csoai-org/councilof-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/csoai-org/councilof-ai/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.

agentmods 80×15 button for councilof-ai CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/csoai-org/councilof-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/csoai-org/councilof-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,593 This file is loaded in full into every session.
When invoked 1,593 The same file — it is already loaded in full.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01593 $0.01593
Opus 5 $0.00796 $0.00796
Sonnet 5 $0.00319 $0.00319
Haiku 4.5 $0.00159 $0.00159

Measured 3d ago against content hash b39c04380ba8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

councilof-ai CLAUDE.md scanned grade B with 2 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 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Mailbox is **[email protected]** on Namecheap Private Email (https://privateemail.com). GitHub sudo codes go there. **Do not use Gmail.**

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Merge gate = GHA `deploy.yml` + `curl -I https://councilof.ai`.
CLAUDE.md · 73 lines

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.

CLAUDE.md — CSOAI / councilof-ai agent coordination

Shared working agreement for ALL agents on this repo. Read this first.

Deployed truth (verified 2026-08-31 — supersedes 2026-08-26)

  • THIS repo → Cloudflare Pages councilof-ai → https://councilof.ai. Vercel Git unlinked; leftover Vercel projects (csoai-v2-app, councilof-ai-src, …) deleted 31 Aug 2026. Do not vercel deploy. Do not wait for Vercel GitHub checks. Merge gate = GHA deploy.yml + curl -I https://councilof.ai.
  • Live board: GET https://councilof.ai/api/gspc → 22 slots · 22 measured · 0 UNMEASURED. Cards: THREE corpora, zero overlap — say which one you mean, every time. Full map + the correct sentence: council-os/CARD-CORPORA.md. In short: · public/cards-bundle.json → card_count = every public/cards/*.json wrapper on disk (1072, read 2026-09-05). Its own generator note: "signs nothing, measures nothing." A build-time aggregate, not an attestation. Not in /api/state. · public/root.json → card_count = the card_sha256 leaves under the SIGNED Merkle root (152, verified 2026-09-05 in ALL THREE of the deployed root.json, the committed root.json and cards-bundle.json → root_card_count, same merkle_root cf9f5488…, same as_of). The 152/153 split this line used to record was build-timing drift and has since closed; if the two disagree again that is timing, not disagreement. /api/state → public_root.card_count, kind catalogued. Its OTS proof covers root.json bytes only. · public/signed/card_index.json = the signed card index (335, n_cards == n_cells == cards[].length), of which 335 verify — /api/state → card_chain.bodies_verified_valid, kind measured, 1 signing key. The only one of the three behind which a check was actually run. /api/state → signed_cards.corpus_relation records SEPARATE_CORPORA with identifier_overlap: 0. Never add them, never reconcile them, never substitute one for another. An earlier revision of this line said the standing "335" figure "matched neither" — true of the first two artifacts, and the reason it needed labelling, but 335 is corpus 3 and is sound. All three numbers are right about their own bytes; the defect was three counts wearing one word. Stamp SIGNED (did:web:csoai.org#board-attestation-1).
  • csoai.org = Cloudflare Pages csoai-site (DID apex). os/app.csoai.org CNAME there.
  • Mailbox is [email protected] on Namecheap Private Email (https://privateemail.com). GitHub sudo codes go there. Do not use Gmail.
  • Full eat: ~/_alignment/ALIGNMENT_2026-08-31.md (Mac home, not in this repo — the repo's own _alignment/ holds only the x402 census). Cursor feed grammar: cite live totals.public_count (22·22·0 after #1077).

Read the full file on GitHub · 73 lines

Changes

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.

  1. 3d ago Changed · +43 tokens per session b39c04380ba8
  2. 6d ago Changed · +22 lines · +577 tokens per session 1ca14e491750
  3. 7d ago Changed · +13 tokens per session a2a46c4bbef8
  4. 11d ago First seen · 51 lines · 960 tokens per session scan B 9ad63b506743

Subscribe to this mod's changes

councilof-ai CLAUDE.md is an instructions file published in the GitHub repository CSOAI-ORG/councilof-ai (0 stars, last pushed today), licensed MIT. It adds 1,593 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

a2aed25519gspcmcpmeasurementx402
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens