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/deeefox/awesome-agent-search/agents-mdgit clone --depth 1 https://github.com/DeeeFOX/awesome-agent-searchWrote 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/deeefox/awesome-agent-search/agents-md)<a href="https://agentmods.dev/instructions/deeefox/awesome-agent-search/agents-md"><img src="https://agentmods.dev/badge/instructions/deeefox/awesome-agent-search/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 | $0.00435 | $0.00435 |
| Opus 5 | $0.00217 | $0.00217 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
awesome-agent-search 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide
Mission
Improve coding-agent search quality with public-safe, privacy-aware search integration practices.
SearXNG is a priority research path, not the only supported approach. Contributions may compare native agent search, MCP search adapters, self-hosted search, hosted search APIs, browser-based retrieval, and local documentation search.
Allowed Contributions
Agents may add or update:
- documentation
- best practices
- examples
- structured registry entries
- validation scripts
- workflows
Agents must not add:
- secrets
- tokens
- cookies
- session material
- personal email addresses
- private endpoints
- local machine paths unless sanitized and strictly necessary
Required Checks Before Commit
Run:
make checkmake validate-registrymake review
Recommended Reading Order
Agents should read:
README.mddocs/positioning.mddocs/architecture.mdregistry/resources.json- the closest example or template for the target ecosystem
Language Rules
- governance, process, and repository-maintenance text: modern English, concise
- examples and best-practice guidance: modern English, concise
- Chinese translations may live in
README.zh-CN.mdanddocs/zh-CN/ - English remains canonical when translations differ
- avoid decorative prose
Submission Rules
Every substantial contribution should clarify:
- problem
- approach
- expected benefit
- privacy considerations
- acceptance criteria
When adding a durable resource, also update registry/resources.json.
When changing registry/resources.json, run make generate-registry-index or make review so docs/registry-index.md stays current.
Use templates/research-report-template.md for research notes and templates/integration-template.md for new integration examples.
Issue vs Patch
Patch directly when the scope is local and validation is straightforward.
Prefer an issue first when the change:
- needs design judgment
- changes ecosystem-wide structure
- introduces a new trust or privacy tradeoff
- depends on external service behavior that is still under investigation
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 · 82 lines · 435 tokens per session scan A fd689f1a2929
awesome-agent-search AGENTS.md is an instructions file published in the GitHub repository DeeeFOX/awesome-agent-search (1 stars, last pushed 3mo ago), licensed MIT. It adds 435 tokens to every session, about $0.0022 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
awesome-ai-coding-agent-tools CLAUDE.md
Instructions for namphuongtran/awesome-ai-coding-agent-tools, covering claude.md, what this repo is, validation commands, markdown lint (matches .github/workflows/lint.yml) and link check (matches .github/workflows/links.yml).
awesome-quant AGENTS.md
AGENTS.md instructions for wilsonfreitas/awesome-quant, covering agents.md, project overview, architecture, work tracking and planning and commands.
mcp-steroid CLAUDE.md
Claude Code instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.
awesome-defold AGENTS.md
Instructions for astrochili/awesome-defold: When asked to process the resource inbox, use GitHub issue #16 unless another issue is named.
anywidget-mcp AGENTS.md
Instructions for peter-gy/anywidget-mcp, covering anywidget-mcp, commands, architecture, dependency rule and state invariant.
autovault CLAUDE.md
Claude Code instructions for autoworks-ai/autovault, covering claude.md, project, common commands, architecture and request flow.