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 clean-clean-cutgit 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/clean-clean-cut)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/clean-clean-cut"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/clean-clean-cut/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/clean-clean-cut"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/clean-clean-cut.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 29 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 | $0.00041 | $0.01048 |
| Opus 5 | $0.00020 | $0.00524 |
| Sonnet 5 | $0.00008 | $0.00210 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
clean-clean-cut 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- clean-clean-cut — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean clean cut
Contract
| Field | Bound contract |
|---|---|
| Trigger | User runs /clean-clean-cut to cut accumulated records and residue under an explicit destructive gate. |
| Authority | Reversible local: deletes only VCS-tracked targets inside an enumerated set (show the exact set before cutting); rollback is version control. No remote mutation. No history rewrite, data migration, credential change, or deletion of untracked or critical data. |
| Side effect | Remove accumulated records, residue, and dependent code elements within the enumerated target set. |
| Done | Purge checklist is confirmed and the enumerated targets are removed; the cut is recoverable through VCS. |
Inputs
- An enumerated target set: the records, residue, and dependent code elements to cut. Each member must be VCS-tracked.
- A purge checklist: the explicit PRE conditions, the INVARIANT that must hold during the cut, and the POST conditions that prove the enumerated set is gone.
- Human approval bound to the enumerated target set. Approval must name the exact set; approval of a wider or narrower set does not authorize the cut.
Procedure
- Enumerate the target set. List every record, residue file, and dependent code element to cut, and state a removal order for the set (leaf-to-root by dependency, or reverse-enumeration order). Reject any member that is not VCS-tracked; an untracked target is out of scope. Done when: every member of the target set is listed, the removal order is stated, and each member is confirmed VCS-tracked by git ls-files or equivalent; untracked members are rejected and named.
- Confirm the PRE conditions: the target set is complete, each member is VCS-tracked, and no member outside the enumerated set is touched. Done when: the target set is confirmed complete, every member is VCS-tracked, and no member outside the enumerated set is identified for touching.
- Publish the purge checklist to the human: the enumerated set, the INVARIANT (only enumerated members change, nothing else), and the POST conditions (each enumerated member is absent and the stated check set passes). Done when: the purge checklist is displayed to the human showing the enumerated set, the INVARIANT, and the POST conditions, and the human confirms receipt before proceeding.
- Wait for human approval that names the exact enumerated set. Do not cut on approval of a different set, on silence, or on model self-authorization. Done when: the human approves cutting the exact enumerated set by naming it, and no approval is accepted for a different set, silence, or model self-authorization.
- Cut the enumerated set only. Remove each member in the order stated in step 1. Do not widen the set, follow dependent chains beyond the enumeration, or preserve history by reflex. Done when: every enumerated member is removed in the stated order, and no file outside the enumerated set was touched (confirmed by git status or equivalent).
- Verify the POST conditions: every enumerated member is absent and the stated check set passes. Done when: every enumerated member is absent from the working tree, and the stated check set passes with its expected results.
- Confirm the cut is recoverable through VCS: the removed members exist in version control history. Done when: each removed member is confirmed present in VCS history by git log or equivalent, proving the cut is recoverable.
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 · -14 tokens per session f075272cc939
- 4d ago First seen · 43 lines · 55 tokens per session scan A e5bad9e060e9
clean-clean-cut is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,048 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 2026-09-03.
Other skills, from other repositories
create-pull-request
Use when asked to create or update a PR, revise its description, or link issue references to its body. Not for multi-PR stacks: use gate-and-merge. Not for releases: use git-workflow-and-versioning.
commit-push-pr
Use when asked to commit, push a feature branch, and open or update a pull request with gh in one pass. Not for a push with no PR: use commit-push. Not for a PR body alone: use create-pull-request.
commit
Use when asked to commit changes, create a typed branch, format history for a changelog, or rewrite messages of HEAD or an unpushed range. Not for pushing or a PR: use commit-push or commit-push-pr.
github-backlog-triage
Use when the user invokes backlog triage for a GitHub repo's open issues and PRs. Not for proactive triage, non-GitHub trackers, or single bug issues: use github-bug-report-triage.
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.
setup-gitignore
Use when the user says set up gitignore, fix gitignore, or untracked files keep appearing. Not for remote, credential, publish, deploy, or irreversible changes.