git-discipline
Skill0 starsChanged 5 months agoMITView on GitHub
Commit and branch discipline for all Xete repos, especially when Claude Code runs semi-autonomously via Remote Control. MUST be used for every commit in every session — atomic commits are the rollback granularity when an agent session goes sideways. Trigger whenever staging, committing, branching, or when a work session begins.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- modaal-agent/skillstheir own version, first seen Nov 15, 2026
- cobusgreyling/grok-build-arsenaltheir own version, first seen Nov 8, 2026
- curvedinf/dev-skillstheir own version, first seen Oct 20, 2026
- Confidence-huang/agent-git-disciplinetheir own version, first seen Oct 13, 2026
- Sapere-IA/sdd-onboarding-kittheir own version, first seen Oct 6, 2026
- devpilotX/skillstheir own version, first seen Sep 22, 2026
Used with
Projects with it also use security-audit.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CloudflareSkillsecurity-audit
Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full/comprehensive/end-to-end reviews, or requested report artifacts.
Also in 3 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- Sapere-IA/sdd-onboarding-kit★ 19same name
- annatchijova/SKILLS★ 9same name
- curvedinf/dev-skills★ 7same name
- cobusgreyling/grok-build-arsenal★ 6same name
- radif-ru/ai-multi-agent-system★ 6same name
- dekoza/oh-my-slop★ 4same name
- modaal-agent/skills★ 2same name
- AL-JANEF/janef-forge★ 1same name
- AL-JANEF/janefskills★ 1same name
- Confidence-huang/agent-git-discipline★ 0same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- doubt-driven-reviewSkill
- gate-backtestSkill
- gate-retrospectiveSkill
- solana-security-hardeningSkill
- spec-and-planSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
When agents write code unattended, commits are the save points.
- Distinctive: line 31
Prefer git revert over history rewriting on shared branches.
- Distinctive: line 32
Before any risky operation (rebase, reset, filter), note the current HEAD SHA in the session so it can be restored.
- Distinctive: line 33
If an agent session produced a tangle: branch from the last good commit and cherry-pick, rather than untangling in place.
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Git Discipline
When agents write code unattended, commits are the save points. Big commits mean big rollbacks.
Commit rules
- Atomic: one logical change per commit, target ~100 changed lines, hard ceiling ~300. If a diff exceeds the ceiling, split it before committing — not after review finds a problem.
- Always green: the repo compiles and tests pass at every commit.
cargo check/cargo test(or the project's test command) runs before every commit, not just before push. A commit that breaks the build destroys its value as a save point. - Message format:
<area>: <imperative summary>plus, when applicable,SPEC-<feature>: task NandDDR: reviews/DDR-<name>.md. The message states WHY when the diff alone doesn't. - No mixed concerns: formatting-only changes, dependency bumps, and logic changes are separate commits. A reviewer must be able to read a logic diff without whitespace noise.
Branch rules
- Feature branches per SPEC:
feat/<spec-name>. Contract work never lands directly on main. - Agent sessions (Remote Control, owl-alpha bulk work) commit to their feature branch freely; merging to main requires the DDR verdict SHIP for contract paths.
- Rebase before merge; main stays linear. Force-push only on your own feature branches.
Session start ritual (Remote Control especially)
git status— confirm clean tree before new work; stash or commit anything dangling with an explicit message.git log --oneline -5— confirm you're building on what you think you are.- Confirm current branch matches the SPEC being executed.
Recovery posture
- Prefer
git revertover history rewriting on shared branches. - Before any risky operation (rebase, reset, filter), note the current HEAD SHA in the session so it can be restored.
- If an agent session produced a tangle: branch from the last good commit and cherry-pick, rather than untangling in place.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

