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 agentmods add instructions/grcengineering/companion/agents-mdgit clone --depth 1 https://github.com/grcengineering/companionWhat 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 | $0.00322 | $0.00322 |
| Opus 5 | $0.00161 | $0.00161 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
companion 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 2d 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.
What it actually says
Agent Instructions
This repo is The GRC Companion.
Canonical Source Order
Treat these as source of truth:
brain/- identity, voice, learning method, primitives.skills/- learning skill contracts.commands/- portable learning-only command contracts.profile/- learner-owned profile schema and examples.knowledge/- citation-grounded corpus.demos/- behavioural examples and transcripts.scripts/- generated context and adapter outputs.docs/- GitHub Pages static landing page.dist/adapters/- generated adapter bundles.
If a generated surface conflicts with canonical source, update canonical source and rerun the build scripts.
Build Loop
Run this after structural changes:
scripts/build-knowledge-index
scripts/sync-skill-manifests
scripts/build-card-pages
scripts/build-adapters
scripts/verify-structure
scripts/run-evals
Boundary
The companion is learning-only.
Do not add skills or commands that:
- assess real vendors
- prep live audits
- author production policies
- run controls
- score a user's programme maturity
- process sensitive evidence as if this were an operational GRC system
If a feature seems useful but operational, move it out of this repo or convert it into a fictional practice scenario.
Adapter Rule
Adapters must be generated from canonical files. Do not hand-edit adapter bundles unless you are fixing the generator and regenerating.
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.
- 2d ago First seen · 52 lines · 322 tokens per session scan A 756f4ecd0b6b
companion AGENTS.md is an instructions file published in the GitHub repository grcengineering/companion (32 stars, last pushed 3mo ago), licensed MIT. It adds 322 tokens to every session, about $0.0016 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 instructions, from other repositories
filegrc AGENTS.md
Instructions for Alignbase/filegrc, covering filegrc repository instructions, purpose, agent-facing product surface, product principles and standards alignment.
compliance-trestle-skills AGENTS.md
Instructions for oscal-compass-lab/compliance-trestle-skills, covering agent instructions for compliance trestle, purpose of this repository, primary directory layout, agent safety rules and legacy ssp, pdf, and docx to oscal workflow.
compliance-trestle-skills GEMINI.md
Instructions for oscal-compass-lab/compliance-trestle-skills, covering gemini cli instructions, repository purpose, key paths, required guardrails and legacy document to oscal quick path.
ai-safe2-framework AGENTS.md
AGENTS.md instructions for CyberStrategyInstitute/ai-safe2-framework, covering ai safe² v3.1 agent entry point, start here, version model, normative interpretation and enforcement planes.
corsair AGENTS.md
Instructions for grcorsair/corsair, covering agents.md — corsair, quick commands (bun), tech stack, tdd workflow (required) and testing conventions.
ATF-AI copilot-instructions.md
Instructions for agronetlabs/ATF-AI, covering atf-ai repository instructions for github copilot, governance boundary, core vs. adapter changes, rwa privileged actions and security.