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/almogdepaz/wolfpack/agents-mdgit clone --depth 1 https://github.com/almogdepaz/wolfpackWhat 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 | $0.00070 | $0.00070 |
| Opus 5 | $0.00035 | $0.00035 |
| Sonnet 5 | $0.00014 | $0.00014 |
| Haiku 4.5 | $0.00007 | $0.00007 |
Grade A, and why
wolfpack 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
Wolfpack EDC Agent Entrypoint
This repo ships deep architectural context generated by EDC.
Runtime mode: advisory; unmatched paths warn-allow.
Read edc-context/index.md first for routing, invariants, and cross-module blast radius. Use edc-context/manifest.json as the authoritative routing/policy contract.
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 · 8 lines · 70 tokens per session scan A 03d012d87a20
wolfpack AGENTS.md is an instructions file published in the GitHub repository almogdepaz/wolfpack (39 stars, last pushed 2d ago), licensed MIT. It adds 70 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 2026-08-30.
Other instructions, from other repositories
PanWatch CLAUDE.md
Instructions for TNT-Likely/PanWatch, covering claude.md, what is panwatch, build & run commands, backend and frontend.
PanWatch AGENTS.md
Instructions for TNT-Likely/PanWatch, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
cairn CLAUDE.md
Instructions for zilet/cairn, covering claude.md, what cairn is, commands, hard requirements and the traps that actually bite.
Atmosphere777 AGENTS.md
AGENTS.md instructions for hanabiovo/Atmosphere777, covering agents.md, 项目目标, 先读这些文件, 结构 and 不可破坏的约束.
termaway CLAUDE.md
Instructions for alexkerber/termaway, covering claude.md, project: termaway, commands, project structure and architecture.
cairn AGENTS.md
Instructions for zilet/cairn, a project described as: Self-hosted wellness OS for training, nutrition and longevity. Connects your labs, lifting, running, food and sleep into one agentic brain that suggests the one thing worth doing today. PWA + REST + MCP server. No scores, no nudges.