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/littlebearapps/pitchdocs/doc-refreshnpx skills add littlebearapps/pitchdocs --skill doc-refreshgit clone --depth 1 https://github.com/littlebearapps/pitchdocsWrote 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/skills/littlebearapps/pitchdocs/doc-refresh)<a href="https://agentmods.dev/skills/littlebearapps/pitchdocs/doc-refresh"><img src="https://agentmods.dev/badge/skills/littlebearapps/pitchdocs/doc-refresh.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 | $0.00086 | $0.02283 |
| Opus 5 | $0.00043 | $0.01141 |
| Sonnet 5 | $0.00017 | $0.00457 |
| Haiku 4.5 | $0.00009 | $0.00228 |
Grade A, and why
doc-refresh 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 4d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Refresh
Philosophy
Generation is solved — PitchDocs handles that. Maintenance is the unsolved problem. After the initial docs suite is created, every release needs a coordinated update: CHANGELOG entries enhanced with benefit language, README features refreshed, user guides amended, AI context files synced, and llms.txt kept current.
/doc-refresh closes the maintenance loop. It works alongside release-please: release-please handles version strings and CHANGELOG scaffolding, /doc-refresh handles prose, features, context, and metrics.
Change Detection Workflow
Step 1: Identify the Boundary
# Latest tag (the "since" point for change detection)
git describe --tags --abbrev=0 2>/dev/null
# If no tags exist, fall back to initial commit
git rev-list --max-parents=0 HEAD
# All commits since boundary
git log $(git describe --tags --abbrev=0 2>/dev/null || git rev-list --max-parents=0 HEAD)..HEAD --oneline --no-merges
# If a version argument was provided (e.g., v1.5.0..v1.7.0)
git log v1.5.0..v1.7.0 --oneline --no-merges
If no tags exist at all, recommend running /readme and /docs-audit fix instead — a full generation is more appropriate than a refresh for a brand-new repo.
Step 2: Parse Conventional Commits
Classify each commit into categories that map to documentation impacts:
| Commit Type | Doc Impact |
|---|---|
feat: |
CHANGELOG, README features, possibly user guides, release notes |
fix: |
CHANGELOG, possibly troubleshooting guides |
docs: |
Verify existing docs are consistent with changes |
refactor: |
AI context files (if architecture changed) |
perf: |
CHANGELOG, README metrics if benchmarks cited |
chore: |
Usually none, unless dependencies changed significantly |
BREAKING CHANGE: |
CHANGELOG with migration note, README, migration guide, release notes |
If the repo does not use conventional commits, fall back to git diff --stat analysis — classify changes by which files they touch (source, tests, config, docs) rather than commit message prefix.
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.
- 4d ago First seen · 184 lines · 86 tokens per session scan A 6e603d73357e
doc-refresh is a skill published in the GitHub repository littlebearapps/pitchdocs (8 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 2,283 once invoked, about $0.0004 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 skills, from other repositories
changelog
Record shipped work in the monthly changelog (append-only). Use when something ships or when asked "what changed", "add to changelog", "release notes", or "what shipped this month".
ship-item
Ship a plan/todo item in a documentation-led repo — run the verify gate, integrate per the repo's model (fast-forward or PR), git mv todo→done with a shipped footer, advance the owning ADR(s) to Implemented, regenerate INDEX, append WORKLOG, update the live snapshot. Use when the user says "ship this", "complete the…
changelog
Generate, update, review, and maintain changelogs using Keep a Changelog format, semantic-release, and conventional commits. Use this skill whenever the user wants to add a changelog entry, prepare release notes, document version changes, generate a changelog from git history, configure semantic-release, understand…
golden-jupyter-dir
Use when testing the goldenjupyterdir golden build.
golden-man-kw
Use when testing the man golden build.
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.