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.
git clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWrote 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/anilcancakir/claude-code-plugins/my_docs)<a href="https://agentmods.dev/commands/anilcancakir/claude-code-plugins/my_docs"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugins/my_docs/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/anilcancakir/claude-code-plugins/my_docs"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code-plugins/my_docs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00014 | $0.01155 |
| Opus 5.5 | $0.00006 | $0.00462 |
| Sonnet 5.5 | $0.00003 | $0.00231 |
| Haiku 4.5 | $0.00001 | $0.00115 |
Grade A, and why
my_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 1mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Update Command
Update documentation for all uncommitted code changes. Handles inline docs (PHPDoc, JSDoc, DartDoc) and project documentation in /docs folder.
Arguments
Parse from $ARGUMENTS:
- --inline-only: Only update inline docblocks, skip /docs folder
- --folder-only: Only update /docs folder, skip inline docs
- --check-only: Report what needs updating without making changes
Default (no args): Update both inline docs and /docs folder.
Execution Steps
Step 1: Identify Changes
# Get changed files
git diff --name-only HEAD
# Filter to code files only
# Exclude: configs, package files, assets, tests
Step 2: Detect Documentation Style
For each file type, detect existing style:
# PHP: Check for PHPDoc
grep -l "@param\|@return" *.php
# JS/TS: Check for JSDoc/TSDoc
grep -l "@param\|@returns" *.js *.ts
# Dart: Check for DartDoc
grep -l "^///" *.dart
# Vue: Check component docs
grep -l "@prop\|defineProps" *.vue
Step 3: Launch Doc Updater Agent
Use the Task tool to run doc-updater:
Task({
subagent_type: "doc-updater",
prompt: `Update documentation for uncommitted changes.
Changed files: ${CHANGED_FILES}
Mode: ${MODE} // inline-only, folder-only, or both
For each file:
1. Detect existing doc style
2. Find undocumented or outdated docs
3. Add/update documentation
Project has /docs folder: ${HAS_DOCS_FOLDER}`
})
Step 4: Process Results
The agent will return a list of changes made:
| Category | Action |
|---|---|
| New docblocks | Added |
| Outdated docs | Updated |
| /docs files | Modified |
Step 5: Check-Only Mode
If --check-only, present report without changes:
# Documentation Audit
## Missing Documentation
### Inline Docs Needed
| File | Item | Type |
|------|------|------|
| `OrderService.php:45` | `calculateTotal()` | Method |
| `order_card.dart:23` | `OrderCard` | Class |
### Outdated Documentation
| File | Item | Issue |
|------|------|-------|
| `UserController.php:78` | `update()` | Missing @throws |
### /docs Updates Needed
| Doc File | Reason |
|----------|--------|
| `docs/api/orders.md` | New endpoint added |
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.
- 1mo ago First seen · 193 lines · 14 tokens per session scan A 03795a3aeaf5
my_docs is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 8mo ago), licensed MIT. It adds 14 tokens to every session and 1,155 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
debug
Systematic debugging with hypotheses and evidence gathering.
review
Structured code review with severity categorization (distinct from Claude Code's PR review).
sparring
Adversarial brainstorming - challenge ideas, find weaknesses.
think
Apply structured thinking frameworks to a problem.
haiku
Switch to Haiku model (fast, cheap).
opus
Switch to Opus model (maximum quality).