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/evilfreelancer/openapi-to-cli/agents-mdgit clone --depth 1 https://github.com/EvilFreelancer/openapi-to-cliWrote 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/evilfreelancer/openapi-to-cli/agents-md)<a href="https://agentmods.dev/instructions/evilfreelancer/openapi-to-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/evilfreelancer/openapi-to-cli/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 5.1 | $0.01056 | $0.01056 |
| Opus 5 | $0.00528 | $0.00528 |
| Sonnet 5 | $0.00211 | $0.00211 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
openapi-to-cli 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 today.
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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openapi-to-cli (ocli) - agent brief
ocli is a TypeScript CLI that turns OpenAPI/Swagger specs into runtime commands. No code generation: every invocation loads a cached spec and builds the command tree on the fly. Profiles live in .ocli/profiles.ini, cached specs under .ocli/specs/. Tests are the specification of behavior; README.md is the public contract.
This file is the canonical top-level brief for every coding agent (Codex, Claude Code, Cursor, others). CLAUDE.md is a symlink to it. Detailed rules live in .cursor/rules/*.mdc and their mirrors in .claude/rules/*.md; Codex receives the Cursor side through the hook bridge in .codex/ (see the last section).
Commands
npm ci # install
npm test # full Jest suite
npx jest tests/<module>.test.ts -t "<title>" # one test
npm run build # tsc, must be clean
bash tests/fixtures/download.sh # large real-spec fixtures (GitHub, Box); their suites skip when absent
Workflow that must not be skipped
- Failing test first. A bug gets a reproduction test, a feature gets a behavior test, in
tests/<module>.test.ts. Run it alone and confirm it fails for the right reason before touchingsrc/. - Minimal change at the lowest layer. Pure (
bm25.ts,command-args.ts) -> I/O wrappers (config.ts,profile-store.ts,openapi-loader.ts) -> transform (openapi-to-commands.ts,command-search.ts) -> entry (cli.ts, the only module that talks to yargs, axios, process). Lower layers never import upper ones. - Green everywhere.
npm testpasses in full andnpm run buildis clean before the work is called done. - README for anything a user can observe. Flags, command names, profile fields,
.ocli/layout, search behavior, supported spec features, authentication and header handling (which requests carry credentials, and to which hosts), spec loading and caching,--helptext, error messages, exit codes. A change counts even when it adds no flag.examples/skill-ocli-api.mdandskills/ocli-api/SKILL.mdstay aligned with the documented agent workflow. - Rules Sync. Any change to a rule file is mirrored between
.claude/rules/and.cursor/rules/in the same commit, and the index in.codex/rules.mdplus the rule list below are refreshed when a rule is added, renamed, or removed.
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.
- today First seen · 46 lines · 1,056 tokens per session scan A 0a595d614461
openapi-to-cli AGENTS.md is an instructions file published in the GitHub repository EvilFreelancer/openapi-to-cli (258 stars, last pushed yesterday), licensed MIT. It adds 1,056 tokens to every session, about $0.0053 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 2026-09-05.
Other instructions, from other repositories
mikro-orm copilot-instructions.md
Copilot instructions for mikro-orm/mikro-orm, covering mikroorm typescript orm development instructions, working effectively, environment setup, building and testing and environment reset (when pulling master).
qq-music-api AGENTS.md
AGENTS.md instructions for Rain120/qq-music-api, covering 🤖 qq music api - ai agents 指南 (agents.md), 🎯 目录, 项目概览, 项目架构 and 1. 服务端主链路.
sportsdataverse-js CLAUDE.md
Instructions for sportsdataverse/sportsdataverse-js, covering claude.md — sportsdataverse (node.js) development guide, package overview, commit convention, branches and build & development commands.
unraid-management-agent copilot-instructions.md
Copilot instructions for ruaan-deysel/unraid-management-agent, covering copilot instructions, copilot workflow, path-specific instructions, reusable prompts and quick commands.
webiny-js copilot-instructions.md
Copilot instructions for webiny/webiny-js, a project described as: Open-source, self-hosted CMS platform on AWS serverless (Lambda, DynamoDB, S3). TypeScript framework with multi-tenancy, lifecycle hooks, GraphQL API, and AI-assisted development via MCP server. Built for developers at large organizations.
sportsdataverse-js copilot-instructions.md
Instructions for sportsdataverse/sportsdataverse-js, covering github copilot instructions — sportsdataverse (node.js), architecture (how the code is generated), conventions and commits / prs.