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 finish-it-nowgit 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/finish-it-now)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/finish-it-now"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/finish-it-now/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/finish-it-now"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/finish-it-now.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.00670 |
| Opus 5 | $0.00035 | $0.00335 |
| Sonnet 5 | $0.00014 | $0.00134 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
finish-it-now 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 5d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finish it now
Contract
| Field | Bound contract |
|---|---|
| Trigger | The user says ship it now, no phases, or finish it now, or the work would otherwise be split into phases, staged rollouts, follow-up PRs, or TODO-later remainders. |
| Authority | Reversible-local: write only the named local implementation artifacts that the ask puts in scope. Rollback is reverting this single change. |
| Side effect | All in-scope implementation paths are written in one change. The change produces no TODO, stub, placeholder, NotImplemented, or follow-up remainder. |
| Done | Every in-scope path is implemented in one change, and anything dropped is named in one line with its reason. |
Inputs
- The ask (required): the work to ship, including every path it puts in scope.
- A phased skill or plan in play (optional): when present, its steps are collapsed into this single pass rather than executed across phases.
Procedure
- Execute the whole ask in one pass. No phase 1 and phase 2, no staged rollout, and no follow-up PR for work already in scope. Done when: the whole ask is executed in one pass.
- Finish every opened path. Write the real implementation instead of leaving a TODO, stub, placeholder, or raised NotImplemented. Done when: every opened path has a real implementation.
- When a phased skill or plan is in play, collapse it to one pass: run its steps back to back in this change and ship the result. While this posture is active it takes precedence over phase-based execution. Done when: any phased plan is collapsed into this change.
- When the ask genuinely exceeds one pass, cut scope instead of deferring it. Name what was cut and why; never hand back a remainder. Done when: scope that cannot fit is cut and named rather than deferred.
- Report only what shipped. Done names the code that is in the tree right now. Done when: the report names only code present in the tree.
Failure and recovery
- Unshipped remainder: a TODO, stub, placeholder, NotImplemented, or phase-2/later/follow-up label is unshipped work. Recover by writing the real implementation; if that is genuinely impossible in one pass, cut scope out loud in one line rather than carry pending work.
- Scope exceeds one pass: cut scope, name what was cut and why in one line, and ship the reduced scope. Never return a deferred remainder or pretend the done predicate holds.
- Partial result: nothing is labeled done until every in-scope path is implemented. A partial change is not done and is not reported as done.
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.
- 5d ago First seen · 36 lines · 70 tokens per session scan A 5420a4da09bb
finish-it-now is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 70 tokens to every session and 670 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
drift-detect
Use when the user says "plan drift", asks whether the roadmap, plans, or docs still match the code, or is deciding what to rebuild when restarting a stalled project. For doc-vs-code drift inside a specific diff, use sync-docs.
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.
setup-repo-skills
Use when the user wants one-time repository setup for tracker, triage labels, and domain conventions. Not for ongoing triage, issue creation, or multi-repo setup.
git-history-analysis
Use when the user asks about recent engineering work, what the team is working on, planning or roadmap material, or an explicitly requested Slack summary. Not for remote or irreversible changes.
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.
graph-backbone
Use when defining, revising, or gate-replanning the project structural backbone in project-root graph.yaml; produces a validated approved revision preserving immutable topology and additive metadata. Not for remote, credential, publish, deploy, or irreversible changes.