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/alberto-codes/docvet/agents-mdgit clone --depth 1 https://github.com/Alberto-Codes/docvetWrote 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/alberto-codes/docvet/agents-md)<a href="https://agentmods.dev/instructions/alberto-codes/docvet/agents-md"><img src="https://agentmods.dev/badge/instructions/alberto-codes/docvet/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 | $0.00760 | $0.00760 |
| Opus 5 | $0.00380 | $0.00380 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
docvet 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docvet
docvet is a Python CLI tool that checks whether docstrings are present, complete, accurate, and renderable. It covers layers 1 and 3-6 of its quality model; layer 2 (style) is handled by ruff.
Quality Model
| Layer | Check | What it catches |
|---|---|---|
| 1. Presence | presence |
Public symbols missing docstrings + coverage reporting |
| 3. Completeness | enrichment |
Missing Raises, Yields, Attributes, Examples, and 6 more sections |
| 4. Accuracy | freshness |
Docstrings that fell out of sync with code (git diff + blame) |
| 5. Rendering | griffe |
Warnings that break mkdocs-material + mkdocstrings output |
| 6. Visibility | coverage |
Packages missing __init__.py (invisible to mkdocs) |
Layer 2 (style) is handled by ruff.
Install
pip install docvet
For griffe rendering checks:
pip install docvet[griffe]
Run
| Command | What it does |
|---|---|
docvet check --all |
Run all checks on entire codebase |
docvet check |
Run all checks on files changed since last commit |
docvet check --staged |
Run checks on staged files only |
docvet enrichment |
Check for missing docstring sections |
docvet freshness |
Detect stale docstrings via git |
docvet coverage |
Find packages invisible to mkdocs |
docvet griffe |
Check mkdocs rendering compatibility |
Use docvet check --all for broad sweeps. Use docvet check or docvet check --staged for incremental workflows.
Configure
Add [tool.docvet] to pyproject.toml:
[tool.docvet]
exclude = ["tests", "scripts"]
fail-on = ["enrichment", "freshness", "coverage", "griffe"]
[tool.docvet.freshness]
drift-threshold = 30
age-threshold = 90
Key options: exclude filters directories, fail-on controls which checks cause a non-zero exit code.
What Each Check Does
- enrichment -- Flags functions, classes, and modules missing required docstring sections (Raises, Yields, Receives, Warns, Attributes, Examples, cross-references, and more). 10 rules.
- freshness -- Detects docstrings that no longer match the code, using git diff (immediate) and git blame (drift over time). 5 rules.
- coverage -- Finds package directories without
__init__.py, which makes them invisible to mkdocs. 1 rule. - griffe -- Captures griffe parser warnings that would break mkdocs rendering. 3 rules.
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 · 78 lines · 760 tokens per session scan A 95a0f2dec1ce
docvet AGENTS.md is an instructions file published in the GitHub repository Alberto-Codes/docvet (9 stars, last pushed 2d ago), licensed MIT. It adds 760 tokens to every session, about $0.0038 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 2026-09-03.
Other instructions, from other repositories
python-skills CLAUDE.md
Instructions for rishapgandhi/python-skills, covering python ai-sdlc framework — master context, agent contract — read before every coding task, non-negotiable rules (always active — no exceptions), file structure and how to prime an agent for a project.
python-skills AGENTS.md
Instructions for rishapgandhi/python-skills, covering agents.md — python ai-sdlc framework, identity, prime directive, project context and skill files (load as needed).
python-skills copilot-instructions.md
Instructions for rishapgandhi/python-skills, covering github copilot custom instructions, role, stack, mandatory rules and code style.
cc-statistics CLAUDE.md
Instructions for androidZzT/cc-statistics, covering claude.md, project, setup, usage and architecture.
claude-ruby-marketplace CLAUDE.md
Instructions for hoblin/claude-ruby-marketplace, covering claude.md, repository purpose, before editing, directory structure and versioning.
plan-forge errorhandling.instructions.md
Error handling patterns — Exception hierarchy, ProblemDetails responses, error boundaries, global exception middleware.