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/shanraisshan/claude-code-hooks/commitgit clone --depth 1 https://github.com/shanraisshan/claude-code-hooksWhat 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 | $0.00015 | $0.00846 |
| Opus 5 | $0.00008 | $0.00423 |
| Sonnet 5 | $0.00003 | $0.00169 |
| Haiku 4.5 | $0.00002 | $0.00085 |
Grade A, and why
commit 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 yesterday.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Create a git commit with an auto-generated message. The first line is a summary, followed by a numbered list of the actions/changes that were executed.
Format
[/command-name][DD-Mon-YY HH:MM AM/PM] N changes
1. First change description
2. Second change description
...
"N changes" refers to the number of actions/changes that were executed during the session — NOT the number of git file changes. Look back through the conversation to find the actions that were taken (e.g., from a workflows:workflow-changelog report's action items, or from a workflows:workflow-add-hook workflow's steps).
Steps
-
Get the command name from
$ARGUMENTS. If empty, ask the user what command or task produced these changes. -
Get the current timestamp by running:
date "+%d-%b-%y %I:%M %p" -
Read
changelog/changelog.mdto get the latest entry's priority actions table. Use the items in that table as the list of changes. If the command name is notworkflows:workflow-changelog, fall back to reviewing the conversation to identify actions. -
Run
git status --shortto see which files were changed. -
Show the user the proposed commit message (title + numbered list) and the files to stage. Ask for confirmation before committing.
-
Stage and commit — one commit per file:
- Create a separate commit for each changed file (per CLAUDE.md Git Commit Rules)
- Each commit message uses the same title line but includes only the change descriptions relevant to that file
- Stage one file at a time with
git add <file>, then commit using a HEREDOC - Format for each per-file commit:
[/command-name][DD-Mon-YY HH:MM AM/PM] N changes 1. Change description relevant to this file 2. Another change relevant to this file - If a single change touches multiple files, include that change description in each relevant file's commit
Example
If /commit workflows:workflow-changelog is run after a session that changed 3 files with 4 total actions:
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.
- yesterday First seen · 85 lines · 15 tokens per session scan A 9a0697885785
commit is a command published in the GitHub repository shanraisshan/claude-code-hooks (532 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 846 once invoked, about $0.0001 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
workflow-claude-settings
Track Claude Code settings report changes and find what needs updating.
development-workflows
Update the DEVELOPMENT WORKFLOWS table by researching all 11 workflow repos in parallel.
implement
Execute phased implementation with validation gates.
workflow-concepts
Update the README CONCEPTS section with the latest Claude Code features and concepts.
plan
Create comprehensive planning documentation for a feature.
research
Research and analyze feature viability - GO/NO-GO decision gate.