Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/taylorleese/claude-toolznpx agentmods add skills/taylorleese/claude-toolz/all-docs-improverWrote 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/taylorleese/claude-toolz/all-docs-improver)<a href="https://agentmods.dev/skills/taylorleese/claude-toolz/all-docs-improver"><img src="https://agentmods.dev/badge/skills/taylorleese/claude-toolz/all-docs-improver.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 5.1 | $0.00108 | $0.01692 |
| Opus 5 | $0.00054 | $0.00846 |
| Sonnet 5 | $0.00022 | $0.00338 |
| Haiku 4.5 | $0.00011 | $0.00169 |
Grade A, and why
all-docs-improver 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 8d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
All-Docs Improver
Audit, score, and improve the documentation surface of a repository — CLAUDE.md, README.md, and docs/**/*.md — to keep contributors and Claude sessions oriented.
This skill writes to doc files. It always presents a quality report and waits for explicit approval before applying any edits.
Workflow
Phase 1: Discovery
Find every relevant doc file. Skip vendored / generated / build directories.
# CLAUDE.md family (handled by claude-md-improver)
find . -name "CLAUDE.md" -o -name ".claude.md" -o -name ".claude.local.md" 2>/dev/null \
| grep -v -E "/(node_modules|\.git|venv|\.venv|dist|build|target)/" | head -50
# READMEs at any depth (skip vendored)
find . -name "README.md" 2>/dev/null \
| grep -v -E "/(node_modules|\.git|venv|\.venv|dist|build|target)/" | head -50
# Everything under docs/
find docs -type f -name "*.md" 2>/dev/null | head -100
If none of the three sets has any files, stop and tell the user there are no docs to audit.
Phase 2: Quality Assessment
Score each file against the rubric appropriate to its type. See references/quality-criteria.md for the full rubrics.
| File type | Rubric source | Owner |
|---|---|---|
CLAUDE.md / .claude.local.md |
claude-md-management:claude-md-improver rubric |
Delegate via the Skill tool — pass through its quality report verbatim |
README.md |
README rubric (this skill) | This skill |
docs/**/*.md |
Docs rubric (this skill) | This skill |
Delegation rule: if any CLAUDE.md files were found, invoke claude-md-management:claude-md-improver via the Skill tool before assessing
READMEs and docs/. Capture its quality report and merge it into the unified report in Phase 3. Do not re-score CLAUDE.md files yourself.
Cross-reference with the actual repo:
- Run (or mentally run) any documented commands; verify they exist in
Makefile,package.json,pyproject.toml, etc. - Check that referenced file paths exist (
ls/Read). - Compare claimed versions against
pyproject.toml/package.json/ lockfiles. - Compare badge URLs and screenshots against current state.
- For docs/ contributor guides, spot-check that referenced commands and file paths are still valid.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 162 lines · 108 tokens per session scan A 1d76621e4abe
all-docs-improver is a skill published in the GitHub repository taylorleese/claude-toolz (3 stars, last pushed 1mo ago), licensed MIT. It adds 108 tokens to every session and 1,692 once invoked, about $0.0005 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…