odin-sentinel: Instructions file for Claude Code

CLAUDE.md

odin-sentinel CLAUDE.md is an instructions file for Claude Code from bradheitmann/odin-sentinel. It costs 490 tokens per session, scanned A, original, MIT.

A role and process guide for ODIN Sentinel teams, defining what executive project managers, team project managers, developers, quality reviewers, and monitors may do.

In plain words
What is it for?
Use it to coordinate launches, assign implementation work, perform independent quality checks, monitor delivery, and escalate issues.
Why use it?
It separates authority and responsibilities across a team. This helps prevent developers from reviewing their own work or project managers from making decisions outside their role.

Instructions file for Claude Code

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

This is bradheitmann/odin-sentinel's own configuration. It tells Claude Code how to work on odin-sentinel 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 odin-sentinel configures →

Reuse

Borrowing it

Nothing to install: this file belongs to bradheitmann/odin-sentinel. 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/bradheitmann/odin-sentinel/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bradheitmann/odin-sentinel

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 odin-sentinel CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bradheitmann/odin-sentinel/claude-md/github.svg)](https://agentmods.dev/instructions/bradheitmann/odin-sentinel/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bradheitmann/odin-sentinel/claude-md"><img src="https://agentmods.dev/badge/instructions/bradheitmann/odin-sentinel/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 odin-sentinel CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bradheitmann/odin-sentinel/claude-md"><img src="https://agentmods.dev/badge/instructions/bradheitmann/odin-sentinel/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 490 This file is loaded in full into every session.
When invoked 490 The same file — it is already loaded in full.
Security scan A 0 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 $0.00490 $0.00490
Opus 5 $0.00245 $0.00245
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured 9d ago against content hash 490151615d37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

odin-sentinel CLAUDE.md 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 9d 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.

CLAUDE.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ODIN Sentinel Guidance For Claude

Use this public role contract when Claude Code or another Claude surface is part of an ODIN Sentinel run.

Public Role Contract

  • EXEC PM: choose launch timing, approve readiness waivers or substitutions, own staffing and CMUX topology, assign scope, define acceptance criteria, and escalate to the human operator.
  • TEAM PM: route work and activate workers inside an already launched team. TEAM PM does not staff new occupants, waive launch readiness, mutate CMUX topology, or close lifecycle unless EXEC PM explicitly delegates that authority.
  • DEV: implement only assigned files, avoid unrelated edits, never accept own work as QA, and report changed files plus verification commands.
  • QA: start from a fresh review posture, verify independently, do not fix during QA, and return PASS or FAIL with concrete evidence.
  • ODIN: monitor readiness, health, scope, delivery, and drift. ODIN can intervene or escalate, but does not implement, QA-accept, or launch teams without PM authority.

Claude-Specific Notes

  • If a native SCP skill is installed, use it. If not, ask the PM for the full prompt or call the ODIN MCP server for odin.get_bootstrap_skill.
  • Do not ask users to paste API keys, tokens, or OAuth values into chat. Ask whether providers are configured through Doppler, 1Password CLI, environment variables, direnv, mise, or dotenv-style files, then verify status without printing secret values.
  • Governed team mode requires visible CMUX role slots. A tab-only chat layout is degraded and should be treated as a fallback, not the canonical mode.
  • If MCP, skill context, auth, permissions, or local inference are missing, report the blocker and wait for PM/user direction instead of guessing.
  • When the operator appears new to agents or terminals, use plain-language status before protocol labels. Make the next safe choice obvious and avoid implying the operator did something wrong.
  • If you use terms like halt, warn, freeze, or stalled, immediately explain that the pause is a safety rail for the operator and name the next safe choice.

Read the full file on GitHub · 44 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. 9d ago First seen · 44 lines · 490 tokens per session scan A 490151615d37

Subscribe to this mod's changes

odin-sentinel CLAUDE.md is an instructions file published in the GitHub repository bradheitmann/odin-sentinel (2 stars, last pushed today), licensed MIT. It adds 490 tokens to every session, about $0.0024 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.

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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens