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/sigee-min/ashfox/agents-mdgit clone --depth 1 https://github.com/sigee-min/ashfoxWrote 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/sigee-min/ashfox/agents-md)<a href="https://agentmods.dev/instructions/sigee-min/ashfox/agents-md"><img src="https://agentmods.dev/badge/instructions/sigee-min/ashfox/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 | $0.00199 | $0.00199 |
| Opus 5 | $0.00100 | $0.00100 |
| Sonnet 5 | $0.00040 | $0.00040 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
ashfox 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.
What it actually says
Repository agent bootstrap
Before changing this repository:
- Read development-manifest.json, the versioned authority for product experience, engineering, workflow, commit, versioning, quality, and architecture rules. Its closed schema is development-manifest.schema.json.
- Use CONTRIBUTING.md for the human onboarding map and verification commands, not as a second rule source.
- Read docs/architecture/codebase.md for ownership and dependency boundaries relevant to the change.
Do not confuse the repository development manifest with the generated Web
Studio /workbench/agent-manifest.json. The latter is sourced from
apps/web/src/features/agent/agentManifest.ts and is the runtime contract for
an agent creating an asset. Do not copy either manifest's rules into this
bootstrap file.
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 · 19 lines · 199 tokens per session scan A 70dc3f475870
ashfox AGENTS.md is an instructions file published in the GitHub repository sigee-min/ashfox (28 stars, last pushed today), licensed MIT. It adds 199 tokens to every session, about $0.0010 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
daz-mcp-server CLAUDE.md
Instructions for bluemoonfoundry/daz-mcp-server, covering claude.md (project index), primary commands, skill modules (reference with @), architecture summary and render api (dazscriptserver native endpoints).
mcp-score AGENTS.md
Instructions for tskovlund/mcp-score, covering mcp-score, architecture, why two approaches?, dev environment and commands.
worldlabs-mcp copilot-instructions.md
Instructions for sandraschi/worldlabs-mcp, covering world labs mcp - copilot instructions and session context (world labs mcp).
comfyui_mcp AGENTS.md
Instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.
cascade-img AGENTS.md
Instructions for laffeyp/cascade-img, covering agents.md, what cascade-img is, and how you drive it, how to operate in this repo, the loop and tools.
agentic-obs CLAUDE.md
Instructions for ironystock/agentic-obs, covering claude.md, project overview, project structure, key technologies and communication flow.