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/koalyptus/ls-apis/agents-mdgit clone --depth 1 https://github.com/koalyptus/ls-apisWrote 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/koalyptus/ls-apis/agents-md)<a href="https://agentmods.dev/instructions/koalyptus/ls-apis/agents-md"><img src="https://agentmods.dev/badge/instructions/koalyptus/ls-apis/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 | $0.03254 | $0.03254 |
| Opus 5 | $0.01627 | $0.01627 |
| Sonnet 5 | $0.00651 | $0.00651 |
| Haiku 4.5 | $0.00325 | $0.00325 |
Grade A, and why
ls-apis AGENTS.md scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `packages/cli/src/qa.ts`: `ls-apis qa` handler — shells out to aggregator QA via `execSync` How it starts
The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ls-apis
Project Structure
ls-apis/
├── package.json # root (workspaces)
├── qa-output/ # QA reports (gitignored)
├── packages/
│ ├── aggregator/ # fetches, normalizes, deduplicates
│ │ ├── src/
│ │ │ ├── aggregate.ts # main orchestration
│ │ │ ├── normalize.ts # entry & category normalization
│ │ │ ├── paths.ts # path utilities
│ │ │ ├── qa/ # QA validation
│ │ │ │ ├── index.ts # QA orchestrator
│ │ │ │ ├── validations.ts # pure validation functions
│ │ │ │ └── tests/ # QA-specific tests
│ │ │ ├── sources/ # pluggable fetchers (*.fetcher.ts)
│ │ │ │ ├── index.ts # fetcher auto-loader
│ │ │ │ └── tests/ # fetcher-specific tests
│ │ │ ├── tests/ # aggregator tests
│ │ │ └── types.ts # ApiEntry, SourceFetcher interfaces
│ │ └── vitest.config.ts
│ ├── cli/ # CLI for searching APIs
│ │ ├── data/
│ │ │ └── apis.json # bundled API data (published with package)
│ │ ├── src/
│ │ │ ├── index.ts # CLI entry point
│ │ │ ├── paths.ts # workspace root resolution
│ │ │ ├── colors.ts # terminal color support
│ │ │ ├── qa.ts # QA command handler
│ │ │ ├── categories.ts # categories command
│ │ │ ├── providers.ts # providers command
│ │ │ └── formatter.ts # output formatter
│ │ └── tests/
│ │ ├── paths.test.ts # path resolution tests
│ │ ├── qa.test.ts # QA wrapper tests
│ │ ├── cli.test.ts # CLI integration tests
│ │ ├── categories.test.ts # categories command tests
│ │ ├── providers.test.ts # providers command tests
│ │ └── config.test.ts # config tests
│ ├── shared/ # Shared types, config, search, paths (consumed by all packages)
│ │ ├── src/
│ │ ├── index.ts
│ │ ├── types.ts # ApiEntry, DataFile, Provider, SearchOptions
│ │ ├── config.ts # Config loading/display (moved from CLI)
│ │ ├── search.ts # Search logic (moved from CLI)
│ │ └── paths.ts # Workspace root resolution
│ └── mcp-server/ # MCP server for AI-friendly API queries (stdio transport)
│ ├── src/
│ │ ├── index.ts # Entry point
│ │ ├── server.ts # McpServer: register tools/resources, then connect
│ │ ├── data.ts # Data loading (apis.json)
│ │ ├── schemas.ts # Zod tool input schemas
│ │ ├── types.ts # ToolName, ResourceUri enums
│ │ ├── handlers/ # SDK v2 registration (registerTool/registerResource)
│ │ │ ├── index.ts
│ │ │ ├── register-tools.ts
│ │ │ ├── register-resources.ts
│ │ │ └── tests/ # protocol-level tests (real Client ↔ McpServer)
│ │ │ ├── helpers.ts
│ │ │ ├── register-tools.test.ts
│ │ │ └── register-resources.test.ts
│ │ └── tests/
│ │ └── data.test.ts
│ ├── vitest.config.ts
│ └── package.json # @ls-apis/mcp-server (private, stdio server)
└── AGENTS.md # instructions for AI agents
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 · 293 lines · 3,254 tokens per session scan A 14ba9348e780
ls-apis AGENTS.md is an instructions file published in the GitHub repository koalyptus/ls-apis (0 stars, last pushed today), licensed MIT. It adds 3,254 tokens to every session, about $0.0163 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.