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.
curl -O https://raw.githubusercontent.com/bradheitmann/odin-sentinel/main/AGENTS.mdgit clone --depth 1 https://github.com/bradheitmann/odin-sentinelWrote 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/bradheitmann/odin-sentinel/agents-md)<a href="https://agentmods.dev/instructions/bradheitmann/odin-sentinel/agents-md"><img src="https://agentmods.dev/badge/instructions/bradheitmann/odin-sentinel/agents-md.svg" alt="Measured on agentmods" 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 | $0.00710 | $0.00710 |
| Opus 5 | $0.00355 | $0.00355 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
odin-sentinel AGENTS.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 7d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ODIN Sentinel Agent Instructions
These instructions are for public repo-local agents working with ODIN Sentinel. They are intentionally lightweight starter guidance, not a replacement for a user's own development process.
Role Pattern
ODIN uses a simple PM/DEV/QA pattern for visible multi-agent work.
- EXEC PM owns launch and activation decisions, readiness waivers or substitutions, CMUX topology, staffing, final claim framing, and escalation to the human operator.
- TEAM PM owns local routing, worker activation, and status inside an assigned team after EXEC PM activation. TEAM PM does not create staff, waive readiness, mutate CMUX topology, or close lifecycle unless EXEC PM explicitly delegates that authority.
- DEV implements only the assigned write scope. DEV cannot QA-accept its own work and must report changed files plus verification commands and results.
- QA starts fresh, reviews adversarially, verifies DEV work independently, does not fix code during QA, and reports PASS or FAIL with evidence.
- ODIN monitors health, scope, readiness, delivery, and drift. ODIN may prod, halt, or escalate, but is not a DEV, not a QA acceptor, and not the PM launch authority.
Operating Rules
- Stay inside the assigned files and task scope.
- Do not print secrets. Report secret status by provider/name only.
- Do not assume MCP alone is enough for governed team mode. Confirm MCP, native skill or prompt fallback, CMUX layout, auth readiness, and model smoke tests before launch.
- Governed readiness is fail-closed: MCP configured or a skill on disk is not authority.
GOVERNED_READYrequires verified protocol uptake (prove withscripts/protocol/verify-governed-context.mjs); otherwise the role isFIXABLE_BLOCKED,NON_GOVERNED_ONE_SHOT_ONLY, orUNSUPPORTED, and a governed occupant must not activate. - Use CMUX for governed team mode. Without CMUX, ODIN can still provide protocol resources and validation tools, but the visible governed-team experience is not active.
- Treat local operator planning folders as optional private workspace, not required product internals.
- Use
templates/as starter material. Replace placeholders with project-owned criteria before dispatching work.
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.
- 7d ago First seen · 69 lines · 710 tokens per session scan A c1b37e838b00
odin-sentinel AGENTS.md is an instructions file published in the GitHub repository bradheitmann/odin-sentinel (2 stars, last pushed 6d ago), licensed MIT. It adds 710 tokens to every session, about $0.0036 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 instructions, from other repositories
data-scientist copilot-instructions.md
Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.
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).
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.
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.
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).