Updated 1d ago
by arbiterForge
codeArbiter
Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.
151 GitHub stars (151)
+4 in 30 days
| Period | New stars |
|---|---|
| Sep 27 | 0 |
| Sep 28 | 0 |
| Sep 29 | 0 |
| Sep 30 | 0 |
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | +1 |
| Oct 4 | +1 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | 0 |
| Oct 13 | 0 |
| Oct 14 | +2 |
| Oct 15 | 0 |
| Oct 16 | 0 |
| Oct 17 | 0 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | 0 |
| Oct 21 | 0 |
| Oct 22 | 0 |
| Oct 23 | 0 |
| Oct 24 | 0 |
| Oct 25 | −1 |
| Oct 26 | +1 |
| Oct 27 | 0 |
| Oct 28 | 0 |
| Oct 29 | 0 |
| Oct 30 | 0 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | 0 |
| Nov 3 | +1 |
| Nov 4 | 0 |
| Nov 5 | +1 |
- 22 skills (22 skills found in its SKILL.md files)
- 8 forks (8 forks)
- 1d ago last update (Last updated 1d ago)
Install
Skills CLI
npx skills add arbiterForge/codeArbiter
Asks which skills and agents to install. Just one: npx skills add arbiterForge/codeArbiter --skill brainstorming — add -g for every project.
Claude Code
git clone https://github.com/arbiterForge/codeArbitercp -r "codeArbiter/core/surface/skills/brainstorming" ~/.claude/skills/
Copies the brainstorming skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add arbiterForge/codeArbiter
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 22 of 158 files.
-
brainstorming
Refine feature and sprint intent into a useful specification. Capture scope, observable criteria and material choices without repeated artifact approval ceremonies.
core/surface/ on GitHub (opens in a new tab)skills/ brainstorming/ SKILL.md -
commit-gate
Create a verified local Git commit when committing changes is requested. Not for explaining commit history, drafting a message only, or postponing a commit. Applies every commit gate and never implies a push or PR.
core/surface/ on GitHub (opens in a new tab)skills/ commit-gate/ SKILL.md -
context-check
Inspect context drift and refresh selected source-backed documents under existing authorization.
core/surface/ on GitHub (opens in a new tab)skills/ context-check/ SKILL.md -
context-creation
Build source-backed project context through bounded inspection, optional agents, and record-level knowledge writes.
core/surface/ on GitHub (opens in a new tab)skills/ context-creation/ SKILL.md -
crypto-compliance
The banned-primitive gate. Routed to when changed code hashes, signs, encrypts, derives keys, generates security-relevant randomness, configures TLS, or imports a crypto library. Rejects broken primitives, disabled TLS verification, and home-rolled crypto; the approved-primitive list lives in security-controls.md. The auth-crypto-reviewer agent is dispatched as the reviewer.
core/surface/ on GitHub (opens in a new tab)skills/ crypto-compliance/ SKILL.md -
debug
Investigate an unexplained defect or unexpected behavior without changing application code. Use for root-cause diagnosis and an evidence-backed handoff, including a bounded unresolved result. Not for implementing a known fix, new features, or explanation-only questions.
core/surface/ on GitHub (opens in a new tab)skills/ debug/ SKILL.md -
decision-lifecycle
Record user-decided ADRs or inspect their health read-only. Preserve attribution and acceptance evidence.
core/surface/ on GitHub (opens in a new tab)skills/ decision-lifecycle/ SKILL.md -
decision-variance
Inspect architectural variances with SMARTS; record only explicit user choices. Report-only requests make no changes.
core/surface/ on GitHub (opens in a new tab)skills/ decision-variance/ SKILL.md -
decompose
Develop greenfield context from a resumable interview recorded as decomposition and knowledge records.
core/surface/ on GitHub (opens in a new tab)skills/ decompose/ SKILL.md -
dispatching-parallel-agents
The parallel fan-out primitive. Routed to by any skill or command that splits work across independent units and dispatches an agent per unit — subagent-driven-development, /sprint, parallel /review. It owns the dispatch/collect/funnel discipline: bound concurrency, isolate units, collect every result, dedupe overlap, and funnel through finding-triage then the read-only verdict-aggregator. Raw age…
core/surface/ on GitHub (opens in a new tab)skills/ dispatching-parallel-agents/ SKILL.md -
executing-plans
Assistive /feature coordinator. Select relevant tasks from a maintained spec/plan, delegate a useful batch when warranted, record verified versus pending checks honestly, and give progress summaries without default human-approval stops.
core/surface/ on GitHub (opens in a new tab)skills/ executing-plans/ SKILL.md -
finishing-a-development-branch
Open a PR or finish branch disposition; route CI watching and post-merge cleanup to their owners. Merge and discard need explicit authority.
core/surface/ on GitHub (opens in a new tab)skills/ finishing-a-development-branch/ SKILL.md -
post-merge-cleanup
Clean up an already-merged local branch after proving containment. Confirm each discard and preserve unique work.
core/surface/ on GitHub (opens in a new tab)skills/ post-merge-cleanup/ SKILL.md -
refactor
Restructure code without changing observable behavior: rename, extract, inline, move, deduplicate, or replace an internal implementation with an equivalent one. Prove parity through unchanged pre-existing tests. Not for new behavior, bug fixes, explanation-only questions, or committing finished work.
core/surface/ on GitHub (opens in a new tab)skills/ refactor/ SKILL.md -
release
Prepare a declared release target, or preview it with --dry-run. Derive its version and require authorization before publication.
core/surface/ on GitHub (opens in a new tab)skills/ release/ SKILL.md -
secret-handling
The secret-source gate. Routed to when changed code reads, writes, or passes a secret — API key, token, password, connection string, signing key, certificate, or any value that grants access. Validates that every secret comes from the approved store and never lands in source, log, test fixture, error response, image, or LLM prompt. The auth-crypto-reviewer agent is dispatched as the reviewer.
core/surface/ on GitHub (opens in a new tab)skills/ secret-handling/ SKILL.md -
security-architecture
Threat-model a sensitive design with STRIDE on request. Read-only analysis of threats, controls, and implementation constraints.
core/surface/ on GitHub (opens in a new tab)skills/ security-architecture/ SKILL.md -
subagent-driven-development
Assistive implementation engine for /sprint and scoped executing-plans work. Follow actual dependencies, implement or delegate coherently, run relevant checks, preserve honest evidence, and advance without artifact approval codes or compulsory reviewer cascades.
core/surface/ on GitHub (opens in a new tab)skills/ subagent-driven-development/ SKILL.md -
tdd
Verify authorized feature, fix, and refactor work with scoped obligations, regression-first fixes, behavioral checks, characterization baselines, coverage, and lint.
core/surface/ on GitHub (opens in a new tab)skills/ tdd/ SKILL.md -
tribunal
Run an opt-in deep codebase audit with persisted findings. Confirm cost before dispatch; filing and telemetry need separate approval.
core/surface/ on GitHub (opens in a new tab)skills/ tribunal/ SKILL.md -
using-git-worktrees
OPTIONAL per-task isolation for autonomous parallel work. Routed to only on explicit opt-in by subagent-driven-development or dispatching-parallel-agents, so parallel units mutate files without colliding. Stands up one worktree per unit, works it in isolation, then integrates each unit back onto the caller's working branch for the caller's single commit-gate + finishing-a-development-branch exit.…
core/surface/ on GitHub (opens in a new tab)skills/ using-git-worktrees/ SKILL.md -
writing-plans
Turn the selected specification into a maintained implementation plan with clear outcomes, useful tasks, dependencies, and verification steps. Drafting uses the existing authorization and does not require artifact approval codes, reviewer receipts, or a frozen implementation script.
core/surface/ on GitHub (opens in a new tab)skills/ writing-plans/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
vibe-coding-cnby tradecatlabs Vibe Coding 非严肃开发的从入门到门入的工具箱
-
ai-devkitby codeaholicguy The control plane for AI coding agents.
-
claude-memby thedotmack Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and inject…
-
oh-my-openagentby code-yeongyu OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
-
claude-code-best-practiceby shanraisshan from vibe coding to agentic engineering - practice makes claude perfect
-
agentic-awesome-skillsby sickn33 2,884+ reusable AI agent skills for Claude Code, Codex, Cursor and Gemini CLI. AAS Core adds local catalog discovery, agent-owned selection…