write-commit

write-commit is a skill for Claude Code from leifericf/agentic-sdk. It costs 40 tokens per session (2,363 once invoked), scanned A, original, MIT.

A guide for creating project commits with Jujutsu, a version-control tool used here alongside Git. It defines the commit message format and the commands for describing, splitting, rebasing, and pushing changes.

In plain words
What is it for?
Use it before committing changes, especially when describing changes, creating new revisions, rebasing, or pushing to a remote repository.
Why use it?
It avoids mixing Git and Jujutsu workflows and keeps commit history and messages consistent.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it before committing changes, especially when describing changes, creating new revisions, rebasing, or pushing to a remote repository.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leifericf/agentic-sdk/write-commit
Install

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.

Any agent
npx skills add leifericf/agentic-sdk --skill write-commit
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code.

Wrote 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.

agentmods badge for write-commit

README.md
[![agentmods](https://agentmods.dev/badge/skills/leifericf/agentic-sdk/write-commit.svg)](https://agentmods.dev/skills/leifericf/agentic-sdk/write-commit)
Your own site
<a href="https://agentmods.dev/skills/leifericf/agentic-sdk/write-commit"><img src="https://agentmods.dev/badge/skills/leifericf/agentic-sdk/write-commit.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,363 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.02363
Opus 5 $0.00020 $0.01182
Sonnet 5 $0.00008 $0.00473
Haiku 4.5 $0.00004 $0.00236

Measured 4d ago against content hash 22f23b787cca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

write-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 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.

skills/write-commit/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

write-commit

Invoke before any commit. The project uses jj (Jujutsu) as the VCS, colocated with git for remote compatibility. jj owns the change model; never commit with raw git.

For the prose craft the subject rides on (active voice, concrete over general, no AI tells), invoke write-prose first. This skill owns the form: the jj workflow, the single-line category-first subject, the categories, the pre-flight check.

jj, not git

The repo has both .git/ and .jj/. jj is the source of truth for the working change; git is the wire format for the remote.

Use:

  • jj st (status), jj log --limit N (history), jj diff -r @ (the current change).
  • jj describe -m "..." to set the message on the current change.
  • jj new for a fresh empty change on top; jj squash to fold into the parent; jj unsquash to split it back out.
  • jj rebase -r <rev> -d <dest> to rebase onto another change.
  • jj git push to push (not git push).

Do not use:

  • git commit (bypasses jj's change model). Use jj describe then jj new.
  • git add / git rm (jj auto-tracks working-copy mutations; no staging step).
  • git stash (no jj analogue). Use jj new to start a fresh change; the current one is preserved.
  • git rebase (use jj's, which understands colocation).
  • git am / git apply (use jj squash or rebase to move work).

If a git command seems necessary, stop and re-read: jj has an equivalent for every common git operation.

Bookmarks mark, they do not develop

Work is a linear stack of commits on the current tip. @ is the working-copy commit; describe it, then jj new to advance. There are no development branches. The protected main bookmark trails the tip and advances to the latest landed commit only at land time, by the maintainer. Never base work on main: forking off main when main lags the tip forks history. A bookmark per major deliverable is named in plain words for what shipped, placed on the last landed commit with @ already advanced. A bookmark never doubles as a dev branch.

Read the full file on GitHub · 210 lines

Changes

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.

  1. 4d ago First seen · 210 lines · 40 tokens per session scan A 22f23b787cca

Subscribe to this mod's changes

write-commit is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 2,363 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 2026-09-03.