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 skills/romiluz13/auto-pi/diff-driven-docsnpx skills add romiluz13/auto-pi --skill diff-driven-docsgit clone --depth 1 https://github.com/romiluz13/auto-piWhat 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 | $0.00065 | $0.00754 |
| Opus 5 | $0.00032 | $0.00377 |
| Sonnet 5 | $0.00013 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
diff-driven-docs 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diff-Driven Docs
Stale documentation is worse than no documentation — it actively misleads. This skill treats docs as a deliverable of every code change, not an afterthought. Just as TDD enforces tests accompany code, diff-driven-docs enforces doc updates accompany changes before the workflow closes.
Step 1: Run the impact classifier (BEFORE any doc work)
Read the diff. Classify impact across 3 layers:
| Diff characteristic | Business | Technical | Audit |
|---|---|---|---|
| Internal utility / helper / type only | SKIP | CHECK | SKIP |
| Test addition, no new pattern | SKIP | SKIP | SKIP |
| Style / formatting change | SKIP | SKIP | SKIP |
| Dependency version bump (no API change) | SKIP | SKIP | SKIP |
| Routine bug fix (existing behavior corrected) | SKIP | CHECK | SKIP |
| Simple refactor (behavior unchanged) | SKIP | CHECK if signatures changed | SKIP |
| New exported function / hook / component | SKIP | CHECK | CHECK |
| New page or route | CHECK | CHECK | CHECK |
| Architectural pattern introduced | SKIP | CHECK | CREATE |
| Technology choice made | SKIP | CHECK | CREATE |
| Breaking change to public API | CHECK | CHECK | CREATE |
| Permission or role change | CHECK | CHECK | CHECK |
| Security or compliance impact | CHECK | CHECK | CREATE or UPDATE |
SKIP business docs if: no user-facing surface changed; only internal utils/types/tests modified. SKIP audit docs if: routine bug fix, style change, test addition, or simple refactor with no new pattern. ALWAYS check technical docs when hooks/components/migrations/schema/routes/exported APIs changed. CREATE an audit doc if: an architectural decision was made, a new pattern introduced, a non-obvious tradeoff accepted, or a dev six months from now would ask "why did we do it this way?"
If all three layers are SKIP: set IMPACT_LEVEL: none and emit a SKIPPED note immediately without opening any doc files.
Step 2: Write only the needed updates
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 · 61 lines · 65 tokens per session scan A c13118209fe2
diff-driven-docs is a skill published in the GitHub repository romiluz13/auto-pi (11 stars, last pushed 16d ago), licensed MIT. It adds 65 tokens to every session and 754 once invoked, about $0.0003 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 skills, from other repositories
ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
teach
Teach the user a new skill or concept, within this workspace.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use…