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/rodolfochicone/rc-project/rc-gitnpx skills add rodolfochicone/rc-project --skill rc-gitgit clone --depth 1 https://github.com/rodolfochicone/rc-projectWrote 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/rodolfochicone/rc-project/rc-git)<a href="https://agentmods.dev/skills/rodolfochicone/rc-project/rc-git"><img src="https://agentmods.dev/badge/skills/rodolfochicone/rc-project/rc-git.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 | $0.00036 | $0.02439 |
| Opus 5 | $0.00018 | $0.01220 |
| Sonnet 5 | $0.00007 | $0.00488 |
| Haiku 4.5 | $0.00004 | $0.00244 |
Grade A, and why
rc-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 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Branch, Push & PR
Take the work currently in this repo from "changes on disk" to "PR opened", stopping for the user's confirmation at every outward-facing step. This skill is standalone — it does not read or require any .rc/ workflow artifacts.
Ask every confirmation question in the user's language. An optional Linear issue (e.g. PROJ-123) may be supplied when the skill is invoked; if present, use it and skip the ticket question.
Always write the PR title and description in Brazilian Portuguese (pt-BR), regardless of the conversation language. Keep the conventional-commit type prefix (feat:, fix:, etc.) in the title; everything else is in pt-BR.
Use a TodoWrite list to track the phases. Run them in order; commit, push, and opening the PR each need their own explicit yes — approval for one step never carries over to the next.
Phase 0 — Gather git state
Before anything else, inspect the real repository state by running:
git rev-parse --is-inside-work-tree # is this a git repo?
git branch --show-current # current branch (empty = detached HEAD)
git symbolic-ref --quiet refs/remotes/origin/HEAD | sed 's@^refs/remotes/origin/@@' # default branch
git status --short # working tree changes
git log --oneline @{u}..HEAD # local commits ahead of upstream
git remote -v # remotes
command -v gh # is the gh CLI available?
Base every later decision on this real state, not on assumptions.
Phase 1 — Inspect & guard
- If this is not a git repo → stop and say so. Don't run anything else.
- If
HEADis detached → stop and ask the user to check out a branch first. - Determine the default branch (the remote HEAD from Phase 0; if unknown, ask the user — commonly
mainormaster). - If the working tree is clean and there are no local commits ahead of the upstream/default → there's nothing to ship: tell the user and stop.
What ships with it
8 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.
- references/automation.md 692 B
- references/resolution-patterns.md 1.8 KB
- references/scripts-tools.md 1.2 KB
- references/strategies.md 8.2 KB
- references/troubleshooting.md 1.5 KB
- scripts/analyze-conflicts.sh 2.9 KB runs code
- scripts/pre-rebase-backup.sh 2.4 KB runs code
- scripts/validate-merge.sh 3.0 KB runs code
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 · 153 lines · 36 tokens per session scan A 4159e7f91fc6
rc-git is a skill published in the GitHub repository rodolfochicone/rc-project (19 stars, last pushed 28d ago), licensed MIT. It adds 36 tokens to every session and 2,439 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 2026-08-30.
Other skills, from other repositories
release
Prepare and publish stable Agent Lightning releases through the repository's version bump, pull-request checks, merge, tag, PyPI trusted-publishing, and versioned-documentation workflows. Use when asked to plan, cut, verify, or explain a release; treat nightly TestPyPI builds as a separate path.
split-commit-into-stack
Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…
release-validation
Use this skill when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally built release bundles on user-approved real hosts and private meshes, deciding release readiness, or producing a formal…
release
Perform Harbor release procedures — version bumping, codegen, committing, pushing, and drafting GitHub releases. Use this skill when the user wants to release a new version of Harbor, bump the version number, create a release on GitHub, run the release codegen pipeline, or anything related to shipping a new Harbor…
release
Run the local Agent Safehouse release flow: inspect commits since the last published release, propose the next SemVer version and changelog, present a dry-run for confirmation, then update changelog, publish the GitHub release, and publish the stable Homebrew tap when confirmed.
push-release
Push to GitHub and optionally bump version to trigger PyPI release.