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 create-pull-requestgit 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/create-pull-request)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/create-pull-request"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/create-pull-request/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/create-pull-request"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/create-pull-request.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 48 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.
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 | $0.00052 | $0.03707 |
| Opus 5 | $0.00026 | $0.01853 |
| Sonnet 5 | $0.00010 | $0.00741 |
| Haiku 4.5 | $0.00005 | $0.00371 |
Grade A, and why
create-pull-request 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 2d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create pull request
Contract
| Field | Bound contract |
|---|---|
| Trigger | User asks to create a PR, open or update a draft PR, write or refresh a PR description, revise an existing PR body for reviewer context, or append GitHub issue and Linear ticket references to a PR body. |
| Authority | Human-gated: requires explicit human invocation and preview confirmation before each remote mutation. The write set is one GitHub PR: create or update its title, body, draft state, head, and base, or append one #### Issues block to its body. Rollback is gh pr edit restoring the prior body or closing the created PR. |
| Side effect | Creates or updates a GitHub PR with a descriptive title and body, optionally as a draft; rewrites an existing PR body; or appends one #### Issues block. Remote mutation on GitHub, bounded to one PR. |
| Done | The mode's done state holds: a created or updated PR whose remote title, body, draft state, head, and base match the preview (full, quick); a remote PR body that gives reviewers context the diff cannot, confirmed by a fresh read (describe); or a fresh remote read showing one non-duplicate #### Issues block with both supplied references (link-issues). |
Inputs
Required:
- Mode: one of
full(default),quick,describe,link-issues. Pick the mode from the user's ask, not by guessing. ghCLI installed and authenticated (gh --version,gh auth status).- For
fullandquick: a current git branch that is notmain/master, with commits ahead of the base branch, and the base branch confirmed against the repository default (quick mode rechecks this and rebases when the branch is stale). - For
describe: a PR number or URL and its diff context, retrieved viagh pr diffandgh pr view --json files. - For
link-issues: a PR identifier accepted bygh pr view, a GitHub issue reference, and a Linear ticket key, all supplied exactly. Do not infer, search for, or substitute a missing identifier. Accept an explicit repository when the PR is not resolvable from the current repository.
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.
- 2d ago Changed · +39 lines · -17 tokens per session c7cfcf71a503
- 5d ago First seen · 79 lines · 69 tokens per session scan A b19d4336c85e
create-pull-request is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 52 tokens to every session and 3,707 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 2026-09-03.
Other skills, from other repositories
git-branchless
Use when asked for multi-commit stack edits, rebases, fixups, or stacked-PR publishing with branchless git idioms. Not for plain-git workflows in repos without branchless.
atomic-issues-prs
Use when the user says "atomic PRs" or requests one issue or PR per logical change. Don't use for single-change pushes or uncommitted change-sets.
post-merge-cleanup
Use when a landed merge, release, or completed change needs its cleanup surface reconciled. Scans for stale TODOs, deprecations, unused flags, and doc gaps. Not for unrelated refactoring.
git-workflow-and-versioning
Use when the user asks for release, version bump, changelog, or branch workflow beyond a single commit. Don't use for single commits or for publishing to a package registry.
lockstep-version-guard
Use when a human invokes the release gate to prove all 28 ODIN plugins share one canonical version. Emits a per-file comparison and exits non-zero on mismatch. Don't use to edit release metadata or for remote, credential, publish, deploy, or irreversible changes.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.