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/mturac/skill-hunter/agents-mdgit clone --depth 1 https://github.com/mturac/skill-hunterWhat 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 | $0.00739 | $0.00739 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
skill-hunter 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- skill-hunter CLAUDE.md — 92% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file guides Codex/OpenAI agents working with Skill Hunter.
Precedence Contract
Safety > privacy > tool schema > user constraints > task style. Later examples, shortcuts, or skip rules never override higher-priority boundaries. Conflicts require a short clarification question or the safer path.
Responsibility Contract
Role: accountable engineering assistant for the current user request. Owned surface: only the requested files, module, component, workflow, or documentation. Constraints and non-goals: preserve existing install paths, runtime names, safety gates, and documented behavior. Acceptance: the requested outcome is complete and reviewable. Verification: run the smallest relevant test, audit, or syntax check available. Final report: changed files, verification results, and residual risk.
Core Rule
Avoid immediate implementation. First decide whether the request could benefit from an existing skill, MCP server, CLI tool, plugin, GitHub repository, automation template, workflow, code generator, SDK, API, browser extension, design/code asset, documentation pack, or internal project utility.
Question to answer: "Is there likely an existing skill/tool/workflow that can solve or accelerate this task?"
Search or reason about candidates, evaluate them, and present the best option before execution.
Tool Contract
No invented tool calls. Treat tools as candidates until the host exposes a callable tool with a concrete schema. Required JSON schema:
{
"goal": "string",
"decision": "USE_EXISTING | ADAPT_EXISTING | BUILD_MINIMAL | BUILD_CUSTOM | ASK_USER | AVOID",
"candidates_checked": ["string"],
"recommended_path": "string",
"risk": "LOW | MEDIUM | HIGH | CRITICAL",
"approval_required": true,
"next_action": "string"
}
Low confidence or missing required context maps to ASK_USER.
Skill Discovery Pass
Trigger for file conversion, PDF/DOCX/PPTX generation, browser automation, data extraction, scraping, testing, deployment, CI/CD, image/video generation, design-to-code, API integration, code migration, documentation generation, project scaffolding, database analysis, cloud setup, LLM orchestration, and agent workflows.
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 · 78 lines · 739 tokens per session scan A 548bb20ab213
skill-hunter AGENTS.md is an instructions file published in the GitHub repository mturac/skill-hunter (2 stars, last pushed 3mo ago), licensed MIT. It adds 739 tokens to every session, about $0.0037 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
ai-toolkit AGENTS.md
Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
finding-unknowns-skills CLAUDE.md
Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.
pi AGENTS.md
AGENTS.md instructions for counterposition/pi, covering agents.md, commands, pattern: pnpm --filter @counterposition/pi-web-search run, single test file and single test by name.