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/coding-dev-tools/deploydiff/agents-mdgit clone --depth 1 https://github.com/Coding-Dev-Tools/deploydiffWhat 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 | $0.00434 | $0.00434 |
| Opus 5 | $0.00217 | $0.00217 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
deploydiff 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 yesterday.
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.
What it actually says
deploydiff
Purpose
Compare deployment configurations across environments. Detect drift between staging and production configs. Preview infrastructure changes with human-readable diffs, cost impact estimation, and rollback commands.
Build & Test Commands
- Install (editable, from this repo):
pip install -e . - Install (prebuilt wheel from the self-hosted index):
pip install --index-url https://coding-dev-tools.github.io/pypi-index/simple/ deploydiff - Install (from source):
pip install git+https://github.com/Coding-Dev-Tools/deploydiff.git - NOTE:
deploydiffis NOT on public PyPI — use the self-hosted index or agit+URL above. - Test:
pytest tests/(orpython -m pytest tests/ -v --tb=short) - Lint:
ruff check . - Build:
pip install build twine && python -m build && twine check dist/* - CLI check:
deploydiff --help
Architecture
Key directories:
src/deploydiff/— Main package (CLI, diff engine, cost estimator, rollback generator)tests/— Test suite.github/workflows/— CI/CD (auto-code-review.yml, ci.yml, pages.yml, publish.yml)dist/— Built distributionsscripts/— Automation scripts
Conventions
- Language: Python 3.10+
- Test framework: pytest
- CI: GitHub Actions (auto-code-review.yml, ci.yml, pages.yml, publish.yml)
- Linting: ruff
- Build system: setuptools
- Package layout: src/ layout
- Dependencies: click, rich, pyyaml, tomli, jinja2
- CLI entry point: deploydiff.cli:cli
- Default branch: main
- Versioning: Semantic versioning (semver)
- Documentation: Markdown
Contributing
See CONTRIBUTING.md for detailed contribution guidelines and development workflow.
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.
- yesterday First seen · 38 lines · 434 tokens per session scan A 204e4840e8a6
deploydiff AGENTS.md is an instructions file published in the GitHub repository Coding-Dev-Tools/deploydiff (2 stars, last pushed 6d ago), licensed MIT. It adds 434 tokens to every session, about $0.0022 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
zenml CLAUDE.md
Instructions for zenml-io/zenml, covering zenml claude code guidelines, project structure, use zenml docs via mcp, code style & quality standards and commenting policy — explain why, not what.
spiceai copilot-instructions.md
Instructions for spiceai/spiceai, covering spice.ai agent instructions, data correctness — absolute top priority, evidence — no claim without a reproduction, build, test, lint (expensive — read first) and git & prs.
spiceai AGENTS.md
Instructions for spiceai/spiceai, a project described as: Add a real-time analytics node to your operational database. Spice is a portable, accelerated SQL query, search, and LLM-inference engine in Rust for data-grounded AI apps and agents.
Cotal AGENTS.md
Instructions for Cotal-AI/Cotal, covering agents.md, what this is, read these first, commands and repository map.
opengeni AGENTS.md
Instructions for Cloudgeni-ai/opengeni, covering agent / automation notes (opengeni), full local stack, architecture notes, pull-request delivery across moving main and keeping these notes current.
devopness AGENTS.md
Instructions for devopness/devopness, covering agents, core flow, shared constraints, monorepo structure and git workflow.