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/motozero/repofinder.io/agents-mdgit clone --depth 1 https://github.com/motozero/repofinder.ioWhat 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 | $0.00510 | $0.00510 |
| Opus 5 | $0.00255 | $0.00255 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
repofinder.io 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 yesterday.
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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RepoFinder
RepoFinder accepts a GitHub repository or public website plus a developer goal. It returns maintained open source repositories that complement the source, with project-specific reasoning and integration guidance.
This repository is also a Codex teaching artifact. Keep the product, lessons, skills, and claims in sync.
Architecture
src/engine.tsowns all recommendation logic throughrecommend(input, goal, env).src/index.tsexposes the browser HTTP API.src/mcp.tsexposes the same engine as therecommend_reposMCP tool.src/openai.tsis the only OpenAI provider boundary.- Surfaces validate and shape requests. They never duplicate engine logic.
Runtime
- Cloudflare Worker with Static Assets and an isolated D1 database.
- TypeScript and ES modules. The frontend is plain HTML, CSS, and JavaScript.
- OpenAI Responses API with strict JSON Schema outputs.
gpt-5.6-lunahandles extraction.gpt-5.6-terrahandles ranking and explanations.- Live GitHub ranking is the labeled fallback when OpenAI is missing or unavailable.
Isolation
All production resources belong to RepoFinder:
- GitHub:
motozero/repofinder.io - Worker:
repofinder-io - D1:
repofinder-io - Domain:
repofinder.io
Do not bind, route, deploy, or store data in RepoRecommender resources.
Security and privacy
- Never commit secrets. Local values live in
.dev.vars; production values use Wrangler secrets. - Keep GitHub access read only and least privilege.
- Bound every public input. Validate public website targets and every redirect to reduce SSRF risk.
- Preserve security headers and the Content Security Policy.
- Do not claim model output is deterministic or authoritative.
Product writing
- Use sentence case headings.
- Be direct and concrete. Avoid filler and marketing superlatives.
- Do not use em dashes or doubled hyphens in prose.
- Clearly label OpenAI-ranked output and fallback output.
Quality gates
Before shipping:
- Run
npm run typecheck. - Run
npm test. - Exercise the affected flow in a real browser.
- Review input validation, secret handling, fallback behavior, and deployment isolation.
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.
- yesterday First seen · 59 lines · 510 tokens per session scan A 8e5f1caa5e0b
repofinder.io AGENTS.md is an instructions file published in the GitHub repository motozero/repofinder.io (1 stars, last pushed 26d ago), licensed MIT. It adds 510 tokens to every session, about $0.0026 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
shippie AGENTS.md
Instructions for mattzcarey/shippie, covering repository guidelines, project structure, build, test, and development commands, coding style and models & mcp.
bountyverdict AGENTS.md
AGENTS.md instructions for cristianmoroaica/bountyverdict, a project described as: Seven x402 decision APIs and installable agent skills for GitHub bounties, CI, skill security, and MCP drift.
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Sharing the learning along the way we been gathering to enable Azure OpenAI at enterprise scale in a secure manner. GPT-RAG core is a Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large…