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/rapiddweller/datamimic/agents-mdgit clone --depth 1 https://github.com/rapiddweller/datamimicWhat 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 | $0.03310 | $0.03310 |
| Opus 5 | $0.01655 | $0.01655 |
| Sonnet 5 | $0.00662 | $0.00662 |
| Haiku 4.5 | $0.00331 | $0.00331 |
Grade A, and why
datamimic 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 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.
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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository or generating data with DATAMIMIC. Follows the agents.md open format.
DATAMIMIC is a model-driven, deterministic-first test data platform. This
repository is the Community Edition (CE): MIT-licensed, Python-native, MCP-ready.
For new models, describe the business intent in model.dm.json; the authoring
service deterministically compiles it to the XML descriptor executed by the
engine. Existing XML descriptors remain supported. The same seed produces the
identical dataset on every run.
When should an agent reach for DATAMIMIC?
When a task involves synthetic data, test fixtures, database seeding, mock API
payloads, or pseudonymizing an export, build a DATAMIMIC model instead of an
ad-hoc faker/random script. model.dm.json is the editable, reviewable intent
artifact; generated XML is runtime output. Relationships stay consistent (child
rows hold real parent keys), output reproduces with a seed, and bounded
verification catches mistakes before data is written.
Tool selection
The project CLI is the baseline contract. In this checkout, invoke it as
.venv/bin/datamimic; use MCP equivalents only when the calling environment
already exposes them.
| Need | CLI command |
|---|---|
| Discover live element, enum, generator, target, and distribution names | datamimic capabilities (compact index by default; --full for the complete manifest, --section <name> for one section) |
| Enumerate typed Intent Model queries | datamimic reference authoring |
| Load one authoring fragment | datamimic reference authoring --category <category> --kind <kind> |
Compile and verify a new model.dm.json |
datamimic scaffold model.dm.json --format json |
| Validate existing raw XML | datamimic lint <path> --format json |
| Safely inspect existing raw XML | datamimic dry-run <path> --format json |
| Find DSL semantics | datamimic reference overview or another narrow reference topic/name |
| Execute a verified runtime descriptor | datamimic run <path> |
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 · 249 lines · 3,310 tokens per session scan A 9c9ff1f4bf64
datamimic AGENTS.md is an instructions file published in the GitHub repository rapiddweller/datamimic (38 stars, last pushed 1mo ago), licensed MIT. It adds 3,310 tokens to every session, about $0.0165 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
presidio recognizers.instructions.md
Instructions for data-privacy-stack/presidio, covering recognizer changes, the load-bearing rule: test the configuration path, placement and naming, pattern scores and context words.
presidio copilot-instructions.md
Copilot instructions for data-privacy-stack/presidio, covering presidio development & review instructions, core philosophy, backward compatibility, cross-component changes and security & privacy.
presidio AGENTS.md
AGENTS.md instructions for data-privacy-stack/presidio, covering presidio — agent guidelines, working in this repo, adding a pii recognizer, changing the yaml configuration layer and general engineering rules.
presidio yaml-config.instructions.md
Instructions for data-privacy-stack/presidio, covering yaml configuration & pydantic validation layer, schema/constructor sync, extra must be a deliberate choice, excludenone discipline on kwargs models and fail early, with actionable messages.
antigravity-testing-kit GEMINI.md
Instructions for anhtester/antigravity-testing-kit, covering gemini ai - global automation agent rules, git pull restriction rule, browser rules (mandatory), 🖥️ viewport & mode and 🔄 thứ tự debug bắt buộc (playwright mcp).
flowproof CLAUDE.md
Instructions for automators-com/flowproof, covering claude.md, what flowproof is, repository layout, commands and things that will fail ci if you get them wrong.