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/sdcorejs/sdcorejs-agent/sdcorejs-gitnpx skills add sdcorejs/sdcorejs-agent --skill sdcorejs-gitgit clone --depth 1 https://github.com/sdcorejs/sdcorejs-agentWhat 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 | $0.00081 | $0.05139 |
| Opus 5 | $0.00041 | $0.02570 |
| Sonnet 5 | $0.00016 | $0.01028 |
| Haiku 4.5 | $0.00008 | $0.00514 |
Grade A, and why
sdcorejs-git 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 — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git
Purpose
One skill for Git artifacts:
- isolate risky or parallel work from the user's current branch
- create a scoped Conventional Commit
- push a verified branch
- open or update a pull request
- write release notes or CHANGELOG entries
Readiness and final delivery gates live in sdcorejs-ship.
sdcorejs-git creates artifacts only. It is not the readiness gate, it must not
repair source files, and it must not create commits, pushes, or PRs as a
substitute for verification.
Shared Protocols
Read _refs/shared/runtime-protocols.md. Apply
_refs/shared/artifact-lifecycle.md and run SDCoreJS Artifact Closure before staging, commit, or push. For multiple worktrees, nested repositories, or
submodules, load _refs/shared/git-closure-contract.mjs; it verifies approved artifacts, emits exact repository-local path sets, and delegates freshness to
_refs/shared/convergence-contract.mjs#evaluateConvergenceHandoff with its verified receipt.
Mode Selection
| Mode | Trigger examples | Output |
|---|---|---|
workspace |
"worktree", "isolate workspace", "do not touch current branch", "run in parallel" | isolated workspace decision plus baseline result |
commit |
"commit", "commit changes", "save changes" | one scoped Conventional Commit |
pr |
"create PR", "open PR", "gh pr create", "PR text" | pushed current branch plus PR URL or local PR draft |
changelog |
"write changelog", "update CHANGELOG", "release notes", "what changed since vX.Y.Z" | Keep a Changelog entry plus semver recommendation |
If multiple modes match, choose the narrowest explicit artifact request:
commit, pr, workspace, and changelog are artifact modes; readiness,
delivery, dependency updates, release readiness, and "is this ready" belong to
sdcorejs-ship.
Mode Precedence Guard
Before any artifact mode, classify the user's intent.
Delegate to sdcorejs-ship first when the prompt includes readiness or delivery
intent such as ship, ready, done, push, merge, release, create PR, open PR,
submit PR, or ready to merge and current ship evidence is missing or stale for
the current HEAD or diff.
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 · 502 lines · 81 tokens per session scan A efd09b3df81f
sdcorejs-git is a skill published in the GitHub repository sdcorejs/sdcorejs-agent (2 stars, last pushed 15d ago), licensed MIT. It adds 81 tokens to every session and 5,139 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
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…