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/eriknewton/sanctuary-framework/agents-mdgit clone --depth 1 https://github.com/eriknewton/sanctuary-frameworkWrote 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/eriknewton/sanctuary-framework/agents-md)<a href="https://agentmods.dev/instructions/eriknewton/sanctuary-framework/agents-md"><img src="https://agentmods.dev/badge/instructions/eriknewton/sanctuary-framework/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 | $0.05474 | $0.05474 |
| Opus 5 | $0.02737 | $0.02737 |
| Sonnet 5 | $0.01095 | $0.01095 |
| Haiku 4.5 | $0.00547 | $0.00547 |
Grade A, and why
sanctuary-framework 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 4d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: Sanctuary & Concordia Security and Sovereignty Review Context
This file is a briefing for any AI coding agent working in these codebases. Read it before making any changes. It is the canonical, model-neutral source of truth for how to work in this repo; tool-specific files (for example CLAUDE.md) import this file rather than duplicating it.
Attribution Rule (MANDATORY)
No public-facing document, README, blog post, plugin manifest, package metadata, or software artifact may reference or attribute CIMC as author or creator of Sanctuary or Concordia. Erik Newton is the sole author. CIMC may be mentioned in internal/biographical context only.
Commit discipline: test baseline enforcement (MANDATORY)
Every commit to Sanctuary main MUST run npm run typecheck && npm test against a clean working tree before staging; block the commit if either fails, if any transform/collection error appears in vitest output, or if the passing-test count drops below the integer in .test-baseline at repo root.
This rule is now backed by structural enforcement, not just instruction:
- Pre-commit hook at
.githooks/pre-commitruns both gates locally on everygit commit. Install once withcd server && npm run install-hooks(copies the hook into.git/hooks/pre-commit). The hook takes ~21 seconds on a modern Mac. Emergency bypass:SKIP_TEST_BASELINE=1 git commit ...(logged to.test-baseline-overrides.logfor audit). - CI check at
.github/workflows/test-baseline-guard.ymlruns the same two gates on every PR and every push to main. This is the second enforcement layer for commits that bypass the local hook with--no-verifyor from uninstalled environments. Seedocs/audit/branch-protection-setup.mdfor the Git branch-protection runbook required to make this check a hard merge gate. - Written instruction (this block) remains the human-facing contract. The structural layers make violations hard; this rule makes the intent explicit so a reviewer or auditor can cite it.
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.
- 4d ago First seen · 110 lines · 5,474 tokens per session scan A 49819c052fdc
sanctuary-framework AGENTS.md is an instructions file published in the GitHub repository eriknewton/sanctuary-framework (8 stars, last pushed today), licensed Apache-2.0. It adds 5,474 tokens to every session, about $0.0274 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
start-technologies AGENTS.md
AGENTS.md instructions for Start9Labs/start-technologies, covering agents.md, layout, build & test (run from the repo root), branches and channels and releases.
bernstein copilot-instructions.md
Copilot instructions for sipyourdrink-ltd/bernstein, covering copilot instructions, architecture, key constraints, before committing and git rules.
pasteguard AGENTS.md
Instructions for sgasser/pasteguard, covering pasteguard agent instructions, project, stack, commands and workflow.
lobu AGENTS.md
Instructions for lobu-ai/lobu, covering repo map, unrecoverable — never do these, facts you cannot derive, ship a change and how to work.
cai CLAUDE.md
Instructions for cai-layer/cai, covering claude.md, what is cai?, design system, build & run and dev.
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.