task-graph-commit-lock

A pattern for taking turns during Git operations in a project where multiple agents work at once. It uses a special task as a lock, meaning only the agent that claims it may perform the protected Git action.

In plain words
What is it for?
Use it to coordinate Git add, commit, pull, rebase, and similar operations among concurrent agents. Agents claim the lock before acting and release it afterward.
Why use it?
It prevents agents from changing Git's shared staging area or history simultaneously, which can cause conflicts, lost commits, or corrupted work.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/oortonaut/task-graph-mcp/task-graph-commit-lock
Any agent
npx skills add Oortonaut/task-graph-mcp --skill task-graph-commit-lock
Clone the repo
git clone --depth 1 https://github.com/Oortonaut/task-graph-mcp

Made for: Claude Code, Codex.

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,926 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00030 $0.01926
Opus 5 $0.00015 $0.00963
Sonnet 5 $0.00006 $0.00385
Haiku 4.5 $0.00003 $0.00193

Measured yesterday against content hash aa89bf742199, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-graph-commit-lock 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 yesterday.

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.

task-graph/skills/task-graph-commit-lock/SKILL.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Commit Lock Pattern

Serialize git operations across multiple concurrent agents using a well-known sentinel task as a mutex. This pattern uses existing task-graph primitives (claim/release) -- no code changes or new tools are needed.

Prerequisite: Understand task-graph-basics for tool reference.


The Problem

When multiple agents work in the same repository concurrently, their git operations can collide:

  • Two agents run git add + git commit simultaneously
  • One agent's git pull --rebase conflicts with another's in-flight commit
  • Merge conflicts arise from interleaved staging and committing

Git's index is a shared mutable resource. Without serialization, concurrent agents produce merge conflicts, lost commits, or corrupted state.


The Solution: Sentinel Task as Mutex

Create a well-known task with a reserved ID (e.g., _lock:git-commit) that serves as a mutex. Agents must claim this task before performing git operations and release it immediately after.

How It Works

The task-graph claiming system already provides the semantics we need:

  1. claim() transitions a task to working (a timed state), which sets exclusive ownership. If another agent already owns it, the claim fails.
  2. update(status="pending") releases ownership by transitioning to a non-timed state, making the task claimable again.

This is exactly a mutex lock/unlock pattern.


Setup: Create the Sentinel Task

The coordinator (or any agent during project setup) creates the sentinel task once:

create(
  id="_lock:git-commit",
  title="[LOCK] Git Commit Serialization",
  description="Sentinel task for serializing git operations. Claim before git add/commit/push, release after. Do NOT complete or delete this task.",
  tags=["lock", "infrastructure"],
  priority=0
)

Important properties of the sentinel task:

  • Fixed well-known ID: _lock:git-commit -- all agents reference this exact ID
  • Never completed: It stays in pending/working cycle forever
  • Priority 0: Should not appear in normal task listings as actionable work
  • Tag lock: Clearly identifies it as infrastructure, not real work

Read the full file on GitHub · 270 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. yesterday First seen · 270 lines · 30 tokens per session scan A aa89bf742199

Subscribe to this mod's changes

task-graph-commit-lock is a skill published in the GitHub repository Oortonaut/task-graph-mcp (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,926 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens