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/claude-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/claude-md)<a href="https://agentmods.dev/instructions/eriknewton/sanctuary-framework/claude-md"><img src="https://agentmods.dev/badge/instructions/eriknewton/sanctuary-framework/claude-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 | $0.00341 | $0.00341 |
| Opus 5 | $0.00170 | $0.00170 |
| Sonnet 5 | $0.00068 | $0.00068 |
| Haiku 4.5 | $0.00034 | $0.00034 |
Grade A, and why
sanctuary-framework 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 6d 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
@AGENTS.md
Claude Code specifics
The canonical, model-neutral agent instructions live in AGENTS.md and are imported above (Claude Code expands the @AGENTS.md import at session start). This section holds only the bits that are specific to Claude Code.
Prose hygiene propagation
The prose-hygiene conventions in AGENTS.md (invariant comments at enforcement sites, cross-file contract pins, failure-mode notes in runbooks, derived constants, named protocol states) bind subagents too: any build-thread or Agent dispatch prompt that touches server/src or operational docs must restate them, because a spawned agent does not inherit this file's context automatically.
Skill routing
When the user's request matches an available skill, ALWAYS invoke it using the Skill tool as your FIRST action. Do NOT answer directly, do NOT use other tools first. The skill has specialized workflows that produce better results than ad-hoc answers.
Key routing rules:
- Product ideas, "is this worth building", brainstorming → invoke office-hours
- Bugs, errors, "why is this broken", 500 errors → invoke investigate
- Ship, deploy, push, create PR → invoke ship
- QA, test the site, find bugs → invoke qa
- Code review, check my diff → invoke review
- Update docs after shipping → invoke document-release
- Weekly retro → invoke retro
- Design system, brand → invoke design-consultation
- Visual audit, design polish → invoke design-review
- Architecture review → invoke plan-eng-review
- Save progress, checkpoint, resume → invoke checkpoint
- Code quality, health check → invoke health
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.
- 6d ago First seen · 30 lines · 341 tokens per session scan A 42b1f298df80
sanctuary-framework CLAUDE.md is an instructions file published in the GitHub repository eriknewton/sanctuary-framework (8 stars, last pushed today), licensed Apache-2.0. It adds 341 tokens to every session, about $0.0017 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.
pasteguard AGENTS.md
Instructions for sgasser/pasteguard, covering pasteguard agent instructions, project, stack, commands and workflow.
technocore-chat AGENTS.md
AGENTS.md instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
lobu AGENTS.md
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
Gemini CLI instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.