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/laa-software-engineering/terfyn/claude-mdgit clone --depth 1 https://github.com/LAA-Software-Engineering/terfynWhat 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 | $0.00060 | $0.00060 |
| Opus 5 | $0.00030 | $0.00030 |
| Sonnet 5 | $0.00012 | $0.00012 |
| Haiku 4.5 | $0.00006 | $0.00006 |
Grade A, and why
terfyn 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 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
Claude instructions
Read and follow @AGENTS.md.
For PR and diff review, use .cursor/skills/code-review/SKILL.md. Significant review findings must be posted as inline code comments on the changed lines whenever possible; the top-level review is for the merge recommendation and concise verdict.
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 · 6 lines · 60 tokens per session scan A 8c6d04ad31d0
terfyn CLAUDE.md is an instructions file published in the GitHub repository LAA-Software-Engineering/terfyn (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 60 tokens to every session, about $0.0003 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
copilot-pro-dev-samples AGENTS.md
Instructions for pnp/copilot-pro-dev-samples, covering agents.md, purpose, repository layout, sample folder naming and required files.
agent-controller AGENTS.md
Instructions for CCDevelopForFun/agent-controller, covering agents.md, what this is, repository layout, setup, build, test and build.
agent-controller CLAUDE.md
Instructions for CCDevelopForFun/agent-controller: Guidance for Claude Code working in this repository.
agent-atlas copilot-instructions.md
Instructions for rebeccapowell/agent-atlas, covering copilot instructions for agent atlas, project overview, repository layout, tech stack and build and run.
copilot-pro-dev-samples copilot-instructions.md
Instructions for pnp/copilot-pro-dev-samples: Microsoft 365 Agents Toolkit (formerly Teams Toolkit) has been rebranded, and users may still use either name.
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.