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/bguivarch/skillforge/commitgit clone --depth 1 https://github.com/bguivarch/skillforgeWhat 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 | $0.00000 | $0.00923 |
| Opus 5 | $0.00000 | $0.00462 |
| Sonnet 5 | $0.00000 | $0.00185 |
| Haiku 4.5 | $0.00000 | $0.00092 |
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Smart Commit
Analyze Git changes and generate a conventional commit message following the Commitizen format.
Arguments
$ARGUMENTS- Optional: Additional context or instructions for the commit message
Instructions
Generate a conventional commit message by analyzing the current Git changes.
Step 1: Gather Git Information
Run these commands in parallel:
git status- See staged and unstaged changesgit diff --cached- See staged changes (what will be committed)git diff- See unstaged changesgit log --oneline -5- See recent commit style for consistency
Step 2: Analyze the Changes
Based on the diff, determine:
-
Type - Choose the most appropriate type:
feat— A new featurefix— A bug fixdocs— Documentation only changesstyle— Formatting, white-space, missing semi-colons (no code change)refactor— Code change that neither fixes a bug nor adds a featureperf— Performance improvementtest— Adding or correcting testsbuild— Changes to build system or dependenciesci— Changes to CI configurationchore— Other changes (tooling, config, etc.)revert— Reverts a previous commit
-
Scope — The area of the codebase affected (optional but recommended):
- Use lowercase, kebab-case
- Examples:
task,auth,api,db,channel,note - Derive from folder structure or feature name
-
Description — A short, imperative summary:
- Use imperative mood ("add" not "added" or "adds")
- Don't capitalize first letter
- No period at the end
- Max 50 characters
-
Breaking Change — If this introduces breaking changes:
- Add an exclamation mark after the scope:
feat(api)!: remove deprecated endpoint - Or add a footer:
BREAKING CHANGE: explanation here
- Add an exclamation mark after the scope:
Step 3: Format the Commit Message
Follow the Conventional Commits specification:
<type>(<scope>): <description>
[optional body]
[optional footer(s)]
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 · 128 lines · 0 tokens per session scan A 8a697e7d6ecb
commit is a command published in the GitHub repository bguivarch/skillforge (3 stars, last pushed 7mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 923 tokens. 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
writing:compound
Capture learnings from successful writing to improve future work.
writing:review
Exhaustive parallel editorial review of written content.
writing:draft
Transform an outline into prose following style preferences.
writing:plan
Transform a topic or brief into a researched outline with sources.
checkpoint
Full memory flush — refresh state.md, append to activity log, route any new decisions/insights, then commit and push.
log-activity
Append a new entry to the activity log for this session.