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 skills add lugassawan/swe-workbench --skill workflow-commit-and-prgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/workflow-commit-and-pr)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/workflow-commit-and-pr"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-commit-and-pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/workflow-commit-and-pr"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/workflow-commit-and-pr.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.04799 |
| Opus 5.5 | $0.00027 | $0.01920 |
| Sonnet 5.5 | $0.00014 | $0.00960 |
| Haiku 4.5 | $0.00007 | $0.00480 |
Grade A, and why
workflow-commit-and-pr 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 1mo 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow: Commit and PR (pre-merge orchestration)
Announce at start: "I'm using the workflow-commit-and-pr skill to {commit / draft a PR / ship this branch}."
When to invoke
- The user wants to commit staged changes ("commit this", "make a commit").
- The user wants to create a PR ("open a PR", "ship this", "create a pull request").
- The user announces feature completion ("I'm done", "I finished the feature", "feature is complete") — preview-only mode.
- The user references a ticket key (
[A-Z]+-\d+, atlassian/Confluence/GitHub URL) AND wants to commit/PR — chainsswe-workbench:ticket-contextfirst.
When NOT to invoke
- The PR is already merged → use
swe-workbench:workflow-cleanup-mergedfor post-merge cleanup. - The user wants to amend or rebase an existing commit → out of scope; do not amend or force-push.
- The user is staging files only (
git add) with no commit intent → no skill needed. swe-workbench:workflow-developmentPhase 5 is currently driving the flow → that path invokesswe-workbench:workflow-commit-and-prdirectly (do not interpose).
Trigger-phrase discipline
The user's exact phrasing determines what action you take. Never escalate without explicit user words.
| Phrase class | Examples | Action |
|---|---|---|
| Preview only | "I finished the feature", "I'm done", "feature is complete", "ready to commit" | Show: diff summary, drafted commit message, current branch name, doc-only [no ci] check. Do NOT commit. Wait for user to escalate to "commit this" or "ship this". |
| Commit only | "commit this", "make a commit", "commit these changes" | Run git commit with the drafted message. Stop. Do NOT push. Do NOT create a PR. Tell the user: "Committed. Reply push to push, or ship to push and open a PR." |
| One-shot ship | "commit and create a PR", "ship this", "ship it", "ship this branch" | Run commit → push → gh pr create. No intermediate pause. Run draft-vs-ready prompt before gh pr create. |
| Push only | "push this", "push it", "push my branch" | git push -u origin <branch>. Stop. No commit. No PR. |
| PR only | "open a PR for what I just pushed", "create a PR" (no staged changes) | Skip commit. Run existing-PR check → draft/ready prompt → gh pr create. |
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.
- 1mo ago First seen · 258 lines · 68 tokens per session scan A 4b191a57cfc7
workflow-commit-and-pr is a skill published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 4,799 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
branch-and-worktree-workflow
Isolates feature work in its own branch or worktree and integrates it cleanly when done. Use this when starting work that should not disturb the current workspace, when several efforts must proceed in parallel on one repository, or when implementation is finished and the change needs merging, rebasing, or splitting…
unslop-commit
Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop ("comprehensive solution", "robust implementation", "leverage", "enhance", "seamlessly", "This commit..."). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when "why"…
precommit
Pre-commit checks — lint:fix -> build -> test.
precommit-fast
Quick pre-commit checks — lint:fix -> test.
release
Bump a plugin's version, write a detailed changelog entry for the upgrade skill to consume, and commit+push. Takes a plugin slug argument identifying which plugin under plugins/ to release. Use this skill whenever the user says "release", "version bump", "cut a release", "changelog and push", or finishes a set of…