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 OutlineDriven/outline-driven-development --skill commit-push-prgit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/commit-push-pr)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/commit-push-pr"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/commit-push-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/outlinedriven/outline-driven-development/commit-push-pr"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/commit-push-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 15 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 42 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00055 | $0.03585 |
| Opus 5 | $0.00028 | $0.01792 |
| Sonnet 5 | $0.00011 | $0.00717 |
| Haiku 4.5 | $0.00006 | $0.00359 |
Grade A, and why
commit-push-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 3d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit, push, and open a pull request
Commit the working tree, push the feature branch to origin, and open or update the pull request with gh. Commit authoring belongs to commit. Title and body authoring belongs to create-pull-request. This skill adds branch placement, the PR target resolution, the push, and the gh call.
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to ship, commit and open a PR, or push and open a pull request for the current work. |
| Authority | Human-gated: the write set is local commits, at most one local feature branch, one push to origin/<branch>, and one pull request created or edited through gh. The skill states the mutation set (push target, commit list, PR target, title, and body summary) before the push and before the gh call. Rollback is git reset --hard <prior-HEAD> for new commits, git branch -D <branch> for a branch this skill created, and gh pr close or gh pr edit restoring the prior body for the PR. No remote mutation without the gate. |
| Side effect | Local commits, at most one local feature branch, one git push to origin, and one PR created or edited on GitHub. No force push. |
| Done | The branch is pushed and the PR exists with the previewed title and body: git status --porcelain is empty, git rev-list --left-right --count origin/<branch>...HEAD prints 0 0, and gh pr view --json url,title,state returns the PR as OPEN. |
Inputs
- Working-tree state (
git status,git diff HEAD): required, gathered by the skill. - Current branch and recent history (
git branch --show-current,git log --oneline -10): required, gathered by the skill. - Remote default branch (
git rev-parse --abbrev-ref origin/HEAD, thengit ls-remote --symref origin HEAD, thengh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'verified againstgit ls-remote --heads origin <default>): required. When every resolver fails, the skill stops; a default branch is never guessed. - Existing PR for the branch (
gh pr view --json url,title,state): required, gathered by the skill.NO_OPEN_PRwhen none exists. - Remotes (
git remote -v) and fork relationship (gh repo view <origin-slug> --json nameWithOwner,parent,defaultBranchRef): required for the PR target. ghinstalled and authenticated (gh auth status): required.- Evidence supplied by the user (URL, image embed, artifact path): optional, placed in the PR body as given.
- User decisions: detached HEAD, unpushed local default-branch commits, an ambiguous PR target, and whether to rewrite an existing PR's description.
What ships with it
1 file 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.
- 3d ago First seen · 80 lines · 55 tokens per session scan A 75bade76766c
commit-push-pr is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 55 tokens to every session and 3,585 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
simplify
Use when the user says "simplify this diff" or asks for a compression pass over a change-set. Not for dead-code sweeps: use deslop.
make-pr-easy-to-review
Use when a human explicitly asks to reshape or annotate one pull request for review. Don't use for pushing the rewritten branch or mutating any remote.
github-operations
WORKFLOW SKILL — Full GitHub contribution lifecycle: branches, conventional commits, issues, PRs, Actions, releases. gh CLI-first with MCP fallback. WHEN: "commit", "push", "open PR", "create branch", "create issue", "cut release", "GitHub operation". DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code…
new-branch-and-pr
Use when a human explicitly asks to ship work through a clean branch and pull request. Don't use for force-pushing, reusing conflicting branches, or widening the change scope.
gh-review-requests
Use when the user asks to find PRs to review or check the team review queue. Not for summarizing PR feedback: use resolve-pr-feedback. Read-only.
review
Structured code review with parallel audit agents, confidence-scored triage, and optional auto-fix. Examines uncommitted changes, staged diffs, commit ranges, or specific paths. Produces a tiered report (MUST-FIX / RECOMMENDED / NIT) backed by evidence, then optionally applies fixes with verification.