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/jaakla/merit_api/agents-mdgit clone --depth 1 https://github.com/jaakla/merit_apiWhat 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 | $0.01320 | $0.01320 |
| Opus 5 | $0.00660 | $0.00660 |
| Sonnet 5 | $0.00264 | $0.00264 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
merit_api 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Codebase guidance for AI coding agents working in this repository.
What This Project Is
Unofficial MCP server and Python SDK for the Merit Aktiva accounting REST API (Estonian/Polish). The project is a uv workspace with two independently publishable packages:
merit_api/— Python SDK (merit-apion PyPI)mcp/— FastMCP server (merit-unofficial-mcp-serveron PyPI)
Commands
# Install all dependencies (both packages)
uv sync --all-extras
# Run SDK tests
uv run --package merit-api pytest
# Run MCP server tests
uv run --package merit-unofficial-mcp-server pytest
# Run a single test file
uv run --package merit-api pytest merit_api/tests/test_read_methods.py
# Run integration tests (requires live Merit credentials)
MERIT_API_INTEGRATION_TEST=true MERIT_API_ID=xxx MERIT_API_KEY=xxx \
uv run --package merit-api pytest
# Start the MCP server locally
uv run --package merit-unofficial-mcp-server merit-unofficial-mcp
There is no separate linting configuration. CI runs pytest for both packages.
Architecture
SDK (merit_api/src/merit_api/)
MeritAPI in client.py is the single entry point. It owns the HTTP session and HMAC-SHA256 request signing: every request body is deterministically serialized (json.dumps with sort_keys=True), then signed with api_id + timestamp + body. Auth params (apiId, timestamp, signature) go on the query string.
Thirteen domain namespaces are instantiated as properties on MeritAPI (e.g. client.sales, client.customers). They all inherit from Namespace in namespaces.py and call self._client._post() or self._client._get(). The client exposes three HTTP methods: _post, _get, and _get_pdf (for base64-encoded PDF responses).
Key SDK behaviours to know:
- Date format: Merit API fields expect
YYYYMMDDstrings._to_yyyymmdd()converts ISO 8601 to this format; use it when passing dates from invoice-list responses (which return ISO 8601) to write endpoints. - Default period:
Namespace._apply_default_period()injects the last 90 days whenPeriodStart/PeriodEndare omitted. - Business errors: Merit returns HTTP 200 with
{"Success": false, "Error": "..."}for errors._raise_for_business_error()detects this and raisesMeritAPIError. - Plain-text responses: Some endpoints (email/e-invoice delivery) return
"OK"as a plain string. The client normalises these to{"Message": "OK", "Success": true}.
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 · 90 lines · 1,320 tokens per session scan A fd46b494330a
merit_api AGENTS.md is an instructions file published in the GitHub repository jaakla/merit_api (6 stars, last pushed 17d ago), licensed MIT. It adds 1,320 tokens to every session, about $0.0066 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
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.
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).
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.