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 commands/filip-podstavec/claude-leverage/docs-syncgit clone --depth 1 https://github.com/Filip-Podstavec/claude-leverageWrote 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/commands/filip-podstavec/claude-leverage/docs-sync)<a href="https://agentmods.dev/commands/filip-podstavec/claude-leverage/docs-sync"><img src="https://agentmods.dev/badge/commands/filip-podstavec/claude-leverage/docs-sync.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 | $0.00032 | $0.00844 |
| Opus 5 | $0.00016 | $0.00422 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
docs-sync 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Branch: !git branch --show-current
Status: !git status --short
Last commit: !git log -1 --oneline
Last commit shortstat: !git diff HEAD~1 --shortstat 2>/dev/null || echo "no previous commit"
Branch diff vs main shortstat: !git diff main...HEAD --shortstat 2>/dev/null || git diff origin/main...HEAD --shortstat 2>/dev/null || echo "n/a"
CHANGELOG present: !ls CHANGELOG.md 2>/dev/null && echo "yes" || echo "no"
Your role
You are orchestrating a documentation-sync workflow:
- Phase 1: a Sonnet-based subagent reads the diff and existing docs, returns prose-direction suggestions with confidence labels.
- Phase 2: you (the main session) apply approved updates using Edit/Write.
You do NOT analyze the docs yourself in the main session. The subagent does that. Your job is to delegate, summarize, get user direction, and then apply edits.
Workflow
-
Determine diff scope:
- If
$ARGUMENTScontains a commit range or branch (e.g.,HEAD~3..HEADorfeature-branch), pass that to the subagent. - If
$ARGUMENTScontains--changelog-only, tell the subagent to skip README/inline doc analysis and focus only on CHANGELOG. - Otherwise let the subagent default to
git diff HEAD~1(last commit).
- If
-
Invoke the
docs-updatersubagent with the scope. Wait for its structured report. -
If the subagent reports "No Update Needed": relay that to the user briefly and stop. Do not propose unsolicited improvements.
-
If updates are needed: present the report's "Documentation Updates Needed" and "CHANGELOG Entry" sections to the user. Each suggestion has a
confidence: high|lowfield - call those out explicitly so the user knows which are obvious wins versus judgment calls. -
Ask for direction. Offer these options:
- Apply all high-confidence items, ask per low-confidence item
- Apply all (including low-confidence)
- Apply only specific items (user picks)
- Skip - user will handle docs manually
Wait for explicit confirmation. Never apply edits preemptively.
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 · 58 lines · 32 tokens per session scan A 71d02b6396cc
docs-sync is a command published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 844 once invoked, about $0.0002 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 commands, from other repositories
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.
history
List past OCR review sessions.
new-sdk-app
Create and setup a new Claude Agent SDK application.
audit-project-github
This file contains GitHub integration for /audit-project.
claudikins-kernel:verify
Post-execution verification gate. Tests, lint, type-check, then see it working.