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 skills/alexei-led/cc-thingz/committing-codenpx skills add alexei-led/cc-thingz --skill committing-codegit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/committing-code)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/committing-code"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/committing-code.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 | $0.00044 | $0.00582 |
| Opus 5 | $0.00022 | $0.00291 |
| Sonnet 5 | $0.00009 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
committing-code 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Changes
Scope: inspect changes, group them, and create normal commits only. Do not rewrite history, amend existing commits, force-push, or stage secrets. Ground the proposal in git status, diff, and recent log output.
Step 1: Gather State
Use scripts/commit-state.sh gather if present; otherwise gather status, diff stat, and recent commits.
The helper is read-only. Treat helper output as a hint, not proof.
If grouping is unclear, inspect the full diff.
- If no changes: say "Nothing to commit" and stop.
- If not a git repository: report "Not a git repository" and stop.
- If detached HEAD or rebase/merge is interrupted: report the git state verbatim and stop.
Step 2: Choose Fast Path or Split Path
Use the fast path when all are true:
- few changed files
- small diff stat
- one coherent purpose from gathered output
- no suspicious paths
- no obvious mix of code, docs, tests, CI, or config for different purposes
Then propose one commit. No deep exploration. No invented split.
If mixed or unclear, inspect the full diff and group by purpose: feature, fix, refactor, docs, config. Use diff evidence, not filenames alone.
Match commit style from recent history.
Step 3: Present Proposed Commits
Proposed commits:
1. feat: add user validation
- src/validate.ts
- src/validate_test.ts
2. docs: update README
- README.md
If the user rejects the grouping, ask for revised grouping and do not proceed until approved.
Step 4: Execute
Never stage likely secrets: .env, keys, certificates, credentials, passwords, tokens, or files that appear to contain secrets. Flag them to the user if detected in changes. This check does not replace secret-scanning tools.
Pause for user approval before any git add or git commit. For one focused commit, one approval gate is enough. For multiple commits, pause before each commit.
If a pre-commit hook rejects, report the hook error verbatim. Do not retry with --no-verify.
Conditional References
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 69 lines · 44 tokens per session scan A 51c32045f19f
committing-code is a skill published in the GitHub repository alexei-led/cc-thingz (35 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 582 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 skills, from other repositories
peekaboo
Provides runtime observation and interaction for native macOS interfaces through accessibility state and screenshots. Use when the task depends on visible or interactive state in a running SwiftUI/AppKit app: what is rendered, focused, selected, enabled, reachable through menus/windows/dialogs, or experienced across a…
seam-probe
This skill should be used when testing or debugging an embedded-runtime boundary exposed through a dynamically loaded C-ABI library or Unix-domain socket, including requests to inspect exports, exercise FFI callbacks, send framed messages, reproduce seam crashes or hangs, fuzz a boundary, or correlate probe output…
electron-playwright-validator
This skill should be used when a user asks to launch, inspect, automate, test, validate, or debug an Electron desktop UI through Playwright/CDP, including blank renderers, runtime import failures, accessibility snapshots, layout defects, click-through flows, or post-change checks. Not for native macOS or mobile apps…
mobile-flows-maestro
This skill should be used when Maestro is explicitly requested or already present and the task is to author, run, or debug iOS/Android Maestro flows; use Maestro MCP; or handle Maestro selectors, system UI, permissions, Keychain, JavaScript, waits, device state, flakiness, or CI. Evidence includes a .maestro directory…
validate-mobile
Run a Maestro flow on an explicitly selected iOS or Android device and report behavioral evidence.
validate-api
Run the project's Hurl scenarios with an OIDC access token passed as a secret variable.