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/api-agent/agents-mdgit clone --depth 1 https://github.com/agoda-com/api-agentWhat 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 | $0.00826 | $0.00826 |
| Opus 5 | $0.00413 | $0.00413 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
api-agent 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Universal agent guidance for this repo.
Why
api-agent turns one GraphQL endpoint or REST OpenAPI spec into an MCP server. Users ask natural-language questions; the server introspects schema, calls the target API, stores tabular data in DuckDB, and runs SQL post-processing when the API cannot filter, rank, join, or aggregate directly.
What
api_agent/__main__.py: ASGI app,/mcp,/healthapi_agent/config.py: TOML-only app settings;API_AGENT_CONFIGselects file pathapi_agent/context.py: MCP request headers ->RequestContextapi_agent/tools/query.py: public{prefix}_querytoolapi_agent/agent/: OpenAI Agents SDK GraphQL/REST flowsapi_agent/rest/schema_loader.py: OpenAPI 3.x + Swagger 2.0 schema loadingapi_agent/rest/polling.py: REST async polling toolapi_agent/recipe/: learned recipe extraction, storage, matching, tool exposureapi_agent/query_response.py: wrapped vs direct CSV response formattingapi_agent/executor.py: DuckDB SQL execution and result shapingtests/: pytest coverage by module and behavior
How
Use deterministic tools first.
uv sync --group dev
uv run pytest tests/ -v
uv run pytest tests/test_foo.py::test_bar -v
uv run ruff check api_agent/ tests/
uv run ruff format --check api_agent/ tests/
uv run ruff format api_agent/ tests/
uv run ty check
Before pushing, run the CI lint shape:
uv sync --group dev && uv run ruff check api_agent/ && uv run ty check && uv run pytest tests/ -q
Run local server:
uv run api-agent
# public: http://localhost:3000/mcp
Run local server with tracing/debug:
OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 \
uv run --no-sync opentelemetry-instrument api-agent
start.sh uses opentelemetry-instrument when an OTEL endpoint is set. Do not manually wire OpenAI Agents SDK trace exporters in app code; openai_agents auto-instrumentation should load OpenAIAgentsInstrumentor.
Useful local override:
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.
- 2d ago First seen · 88 lines · 826 tokens per session scan A 51b3a472de33
api-agent AGENTS.md is an instructions file published in the GitHub repository agoda-com/api-agent (284 stars, last pushed 2mo ago), licensed MIT. It adds 826 tokens to every session, about $0.0041 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 2026-08-30.
Other instructions, from other repositories
gorest AGENTS.md
Instructions for pilinux/gorest, covering agents.md, project overview, build and run commands, build and tidy dependencies.
gmgn-skills CLAUDE.md
Instructions for GMGNAI/gmgn-skills, covering claude.md, critical rule — read this first, project overview, available skills and quick decision guide.
cli AGENTS.md
Instructions for nylas/cli, covering ai coding agent guidelines, quick reference: shared helpers, quick reference: adding a new feature and quick reference: credential storage.
nango CLAUDE.md
Claude Code instructions for NangoHQ/nango, a project described as: Build product integrations with AI.
mcp-agent-langchainjs AGENTS.md
Instructions for Azure-Samples/mcp-agent-langchainjs, covering mcp agent langchain.js project instructions, architecture overview, component communication flow, key architectural patterns and authentication & state management.
silkweave CLAUDE.md
Instructions for silkweave/silkweave, covering claude.md, commands, mcp inspector (connects to mcp stdio example via .mcp.json), architecture and packages.