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/agoda-com/agent-catalog-eval/agents-mdgit clone --depth 1 https://github.com/agoda-com/agent-catalog-evalWrote 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/agoda-com/agent-catalog-eval/agents-md)<a href="https://agentmods.dev/instructions/agoda-com/agent-catalog-eval/agents-md"><img src="https://agentmods.dev/badge/instructions/agoda-com/agent-catalog-eval/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 | $0.01722 | $0.01722 |
| Opus 5 | $0.00861 | $0.00861 |
| Sonnet 5 | $0.00344 | $0.00344 |
| Haiku 4.5 | $0.00172 | $0.00172 |
Grade A, and why
agent-catalog-eval 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 3d 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.
flow). Mock at seams (`OpenAI` client, `child_process.spawn`). How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guide for AI coding agents working in this repo. Read this before making changes.
What this repo is
agoda-agent-catalog-eval is a public CLI (agoda-agent-catalog-eval on npm) that
evaluates coding-agent skills against a catalog of test cases. Users point
it at a directory of cases and it runs an agent (Cursor / OpenCode / Claude
Code) on each one, then scores the result with an LLM judge.
Layout
agent-catalog-eval/
├── packages/
│ ├── agent-catalog-eval/ ← the published package (src/, tests, tsup, vitest)
│ └── typescript-config/ ← shared tsconfig base.json
├── .github/workflows/ ← checks.yml (PR/push), changeset.yml (publish)
├── .actions/setup/ ← composite action: pnpm + Node 22 + install
├── .changeset/ ← Changesets config + pending changesets
├── eslint.config.js ← flat-config ESLint, applies repo-wide
├── turbo.json ← build/test/check-types pipeline
└── pnpm-workspace.yaml
Source files (packages/agent-catalog-eval/src/)
| File | Role |
|---|---|
cli.ts |
Entry. Calls parseCliArgs, runAll, optionally reportMetrics. |
cli-parser.ts |
Pure parser. Returns {kind: "config" | "help" | "error"}. Add new flags here. |
runner.ts |
Test discovery, execution loop, summary printing. |
agent.ts |
Spawns cursor / opencode / claude in their own process group. |
judge.ts |
OpenAI-based scoring + failure diagnosis. |
files.ts |
Snapshot / copy / cleanup helpers. |
telemetry.ts |
buildPayload + reportMetrics POST. |
ci.ts |
detectCiContext() for GitLab/GitHub/TeamCity/AppVeyor. |
repo-root.ts |
Finds nearest .git ancestor. |
types.ts |
Shared types. |
index.ts |
Public package surface. |
Tests sit alongside (*.test.ts) and use vitest.
Working in the repo
pnpm install
pnpm build # tsup → dist/cli.cjs + dist/index.{js,cjs,d.ts}
pnpm test # vitest (50+ tests)
pnpm check-types # tsc --noEmit
pnpm lint # eslint .
pnpm format # prettier --write
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.
- 3d ago First seen · 160 lines · 1,722 tokens per session scan A b2407deb64f2
agent-catalog-eval AGENTS.md is an instructions file published in the GitHub repository agoda-com/agent-catalog-eval (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,722 tokens to every session, about $0.0086 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.