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/takeoff69/codex-skills-kit/git-under-contentionnpx skills add TAKEOFF69/codex-skills-kit --skill git-under-contentiongit clone --depth 1 https://github.com/TAKEOFF69/codex-skills-kitWrote 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/takeoff69/codex-skills-kit/git-under-contention)<a href="https://agentmods.dev/skills/takeoff69/codex-skills-kit/git-under-contention"><img src="https://agentmods.dev/badge/skills/takeoff69/codex-skills-kit/git-under-contention.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 | $0.00071 | $0.00960 |
| Opus 5 | $0.00036 | $0.00480 |
| Sonnet 5 | $0.00014 | $0.00192 |
| Haiku 4.5 | $0.00007 | $0.00096 |
Grade A, and why
git-under-contention 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Under Contention
Preserve every participant's work when repository state may change concurrently.
Core rule
Treat shared checkout as contested state. Stage exact paths, commit only owned changes, and leave unfamiliar hunks untouched.
Preflight
Run bundled detector before first commit in shared checkout:
python <skill-dir>/scripts/contention_preflight.py
python <skill-dir>/scripts/contention_preflight.py --mine path/owned-by-task
Signals include registered worktrees, recent HEAD movement, pre-staged files, and dirty paths outside owned pathspecs. CONTENTION is not automatic failure – it means use isolated worktree or stricter path ownership.
Skip detector only inside isolated worktree created for current task and still run normal status checks.
Shared-checkout rules
- Inspect
git status --porcelain, current branch, top-level path, and staged diff before mutation. - Stage with
git add <path>...; avoidgit add .,git add -A, andgit commit -a. - Review
git diff --cached --name-onlyandgit diff --cachedbefore commit. - Commit with explicit pathspec when repository conventions allow it.
- Leave changes outside owned paths unchanged, staged or unstaged.
- Avoid stash in contested checkout because stash captures shared state. Use task worktree or WIP commit on owned branch.
- Fetch before deciding branch freshness; do not reset shared checkout to match remote.
- Push durable work promptly so recovery does not depend on one disk.
Worktree lifecycle
Prefer worktree per task when work is multi-file, long-running, risky, or parallel.
- Fetch remote and create short-lived branch from intended base.
- Create worktree at explicit validated path.
- Record absolute root, branch, and base commit in handoff.
- Edit, stage exact paths, commit, and push as one durable sequence.
- Recheck dirty state and unpushed commits before cleanup.
- Remove worktree only through repository helper when one exists.
Before recursive worktree cleanup, inspect symlinks, junctions, mounts, and dependency links. Remove links safely before recursive deletion so cleanup cannot traverse into another checkout.
What ships with it
2 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 · 103 lines · 71 tokens per session scan A f9fda51dd749
git-under-contention is a skill published in the GitHub repository TAKEOFF69/codex-skills-kit (7 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 960 once invoked, about $0.0004 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.
Other skills, from other repositories
manage-codex-skills
Inventory, classify, route, catalog, relocate, or validate Codex skills and generate a skills menu. Use for skill-library organization or when Codex must find task-relevant skills. Classification, relocation, creation, revision, and promotion require user approval.
reflect-codex-workflows
Compare evidence from a current or completed project with installed skills and decide whether to reuse, revise, create, or not skill the lesson. Use for workflow reflection or proposed skill upgrades. Do not edit skills without explicit authorization.
bootstrap-codex-workspace
Inspect a Windows or macOS Codex environment and produce a read-only, approval-bound plan for the global AGENTS.md path, user skills root, and root for future projects. Use for workspace setup, bootstrap, or location planning. Do not write outside the repository until the user approves the exact plan ID.
maintain-project-ai-records
Initialize and maintain lightweight AI work records in a writable project. Use on the first substantive writable task and after meaningful milestones. Do not create records for read-only inspection or trivial answers.
organize-codex-projects
Choose a location and internal structure for a future Codex project, including focused projects and umbrella projects with durable subprojects. Use when creating or planning a new project. Do not move, rename, or normalize existing projects.
eco-max
Maximum-savings variant of eco - the same frugality rules with a tighter reply budget, for routine chores (rename, small fix, quick lookup, boilerplate). Prefer plain eco for hard or high-stakes work. Works in any language.