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 skills add cboone/agent-harness-plugins --skill commitgit clone --depth 1 https://github.com/cboone/agent-harness-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/skills/cboone/agent-harness-plugins/commit)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/commit"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/commit/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/skills/cboone/agent-harness-plugins/commit"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/commit.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 | $0.00033 | $0.03380 |
| Opus 5.5 | $0.00013 | $0.01352 |
| Sonnet 5.5 | $0.00007 | $0.00676 |
| Haiku 4.5 | $0.00003 | $0.00338 |
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 5d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
Create smart, context-aware git commits with conventional commit messages.
Core Principle: Small Logical Chunks
Always prefer committing in the smallest logical chunks that are appropriate. Each commit should represent a single coherent change: one bug fix, one new function, one refactor, one documentation update, etc. Do not batch unrelated changes into a single commit.
Why this matters:
- Small commits are easier to review, revert, cherry-pick, and bisect.
- Each commit tells a clear story about one thing that changed and why.
- When something breaks, small commits make it straightforward to identify the cause.
What constitutes a "logical chunk":
- A single bug fix (even if it touches multiple files)
- A single new feature or capability
- A refactor that moves or renames code without changing behavior
- A documentation update
- A configuration or tooling change
- Test additions or updates for a specific feature
What does NOT belong in the same commit:
- A bug fix mixed with an unrelated refactor
- A new feature combined with formatting changes to unrelated files
- Documentation updates bundled with code changes they do not describe
Options
The user may provide these options inline:
- --push: Commit and push to remote after committing
- --staged: Commit only staged changes (ignore unstaged changes)
- --plan: Commit only the plan file
- --all: Stage and commit all changes (including untracked files)
Skill dependencies
- Required: None
- Optional:
trim-text
Workflow
1. Check for Changes
Run these commands in parallel to understand the current state:
# See all changed and untracked files
git status
# See staged changes
git diff --cached
# See unstaged changes
git diff
# See recent commit messages for style reference
git log --oneline -10
If there are no changes at all (no staged, unstaged, or untracked files), report that there is nothing to commit and stop.
2. Determine What to Commit
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.
- 5d ago Changed · +19 lines 6ff38ec66b18
- 15d ago Changed · +1 lines 4bb7c32ef79f
- 26d ago Changed · -3 lines · -44 tokens per session b2af811f10f0
- 1mo ago Changed · +12 lines c1b11be628b7
- 1mo ago First seen · 231 lines · 77 tokens per session scan A adee8667fe17
commit is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 3,380 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 skills, from other repositories
oz-report-pr
Report a pull request back to the Oz platform after creating one.
commit
Use when making any git commit. Pass the failure, false claim, or risk the changes fix as the argument; for an addition or a filled gap, pass what it adds — never an invented why.
vellum-github-app-setup
Create and configure a GitHub App so the assistant can push commits, open PRs, and comment under its own bot identity. Use when the user wants the assistant to have its own GitHub identity, or when setting up git push access for the first time.
git-hooks-manager
Setup and manage git hooks for pre-commit, pre-push automation (lint, test, format).
avatar-contribution-pr
Turn an avatar GitHub issue (from the in-app avatar-editor easter egg) into a merged sprite — validate the art, then either add a new module or replace an existing one, and open a PR that closes the issue. Handles both "Avatar contribution: " (a brand-new sprite) and "Avatar edit: " (a hand-redraw of an existing…
skillshare-app-pr
Take a change to the skillshare desktop app (runkids/skillshare-app) from request to merged PR: worktree branch, implementation, the full CI checks, a screenshot of the running app in the dev container, a Conventional Commit, a PR, and a merge only on green CI. Use for any code, UI, icon or doc change the user wants…