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/nirecom/agents/commit-pushnpx skills add nirecom/agents --skill commit-pushgit clone --depth 1 https://github.com/nirecom/agentsWhat 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 | $0.00018 | $0.02393 |
| Opus 5 | $0.00009 | $0.01196 |
| Sonnet 5 | $0.00004 | $0.00479 |
| Haiku 4.5 | $0.00002 | $0.00239 |
Grade A, and why
commit-push scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit staged/unstaged changes, push to the remote, and open or reuse a PR.
Pre-commit check
If tests are missing or the commit hook blocks due to missing tests:
- Never write tests directly in this conversation.
- Invoke the
/write-testsskill first, then resume commit-push.
If documentation is missing or the commit hook blocks due to missing documentation updates:
- Invoke the
/update-docsskill first, then resume commit-push.
Phase 1 (issue-close-stage) pre-flight
Run: "$AGENTS_CONFIG_DIR/bin/detect-non-github.sh" "Phase 1 pre-flight" || NON_GITHUB=1
When NON_GITHUB=1 (non-GitHub remote): skip the entire pre-flight block below (including check-phase1-complete.sh), then proceed with commit/push as normal — do NOT abort the skill.
When the command exits 0 (GitHub remote, or unknown/fail-open): run the pre-flight as normal.
Skip message on non-GitHub remote (emitted by the script to stdout): [GITHUB_ISSUES disabled: non-GitHub remote detected, skipping Phase 1 pre-flight]
For each issue N in the session's closes_issues list (parsed from
${WORKFLOW_PLANS_DIR:-$HOME/.workflow-plans}/<session-id>-intent.md —
the ## Issues section; canonical parser: hooks/lib/parse-closes-issues.js — do not reimplement),
run from the worktree root:
bash "$AGENTS_CONFIG_DIR/bin/github-issues/check-phase1-complete.sh" <N>
Non-zero → abort /commit-push and surface stderr (it names the missing
condition: sentinel, history entry, or both). Resolve by invoking
/issue-close-stage <N> from the linked worktree, then re-run /commit-push.
Skip this pre-flight when:
closes_issuesis empty, or the session intent file is missing.- Running from the main worktree (main-worktree commit-push is only valid when
ENFORCE_WORKTREE=off, where the 2-phase split does not apply).
Procedure
Read rules/github-issues.md before CP-1 — on-demand-only, never auto-injected.
Read rules/coding.md before CP-2 — on-demand-only, never auto-injected; its Public GitHub Rules govern the commit message and PR body.
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.
- yesterday First seen · 121 lines · 18 tokens per session scan A 961ecbc721f6
commit-push is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 2,393 once invoked, about $0.0001 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…