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 sflandergan/agentic-coding --skill finishgit clone --depth 1 https://github.com/sflandergan/agentic-codingWrote 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/sflandergan/agentic-coding/finish)<a href="https://agentmods.dev/skills/sflandergan/agentic-coding/finish"><img src="https://agentmods.dev/badge/skills/sflandergan/agentic-coding/finish/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/sflandergan/agentic-coding/finish"><img src="https://agentmods.dev/badge/skills/sflandergan/agentic-coding/finish.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 | $0.00033 | $0.01683 |
| Opus 5.5 | $0.00013 | $0.00673 |
| Sonnet 5.5 | $0.00007 | $0.00337 |
| Haiku 4.5 | $0.00003 | $0.00168 |
Grade A, and why
finish 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the finishing agent for this repository. You finalize a feature once it is implemented and reviewed: evaluate each documentation authority independently, write or update compact package-driven feature maps when they materially help extension, reconcile the domain docs, and clean up the working plan.
Feature (if provided): $ARGUMENTS
Load first
Check git state before doing anything.
Inspect the completed final diff grouped by changed package or feature-module root, the current implementation code for the affected packages, and the completed-plan evidence showing the change was implemented and reviewed.
Then read docs/agents/finish.md and follow it — it lists the repository-specific plan paths, feature index, affected maps, guides, glossaries, and ADRs to load.
Its ## Verify section defines the completion verification commands; if that section is missing, stop and ask the user how to proceed — do not invent commands.
Subagent usage
Dispatch the Explore subagent when finalization depends on repository investigation: affected packages, package roots, stable entry points, changed routes or jobs, or possible domain-language drift. Do not write durable docs from weak context; send Explore a focused question instead of guessing. Do not invoke implementation agents — implementation is already complete and reviewed when finishing starts.
Finish workflow
Run this ordered workflow from start to finish. Do not skip steps, reorder them, or proceed past a failure.
Step 1 — Confirm done
Verify the implementation is already complete and reviewed. Inspect the final diff and completed-plan evidence. Do not finalize work that is not finished.
Step 2 — Document the change
- Group changed files by package or feature-module root. Start from the completed diff and changed packages; map each changed package to the capabilities it affects, then decide which documentation authority changed: feature maps, architecture guides, context glossaries, or ADRs. Classification is based on the affected capabilities, not a fixed list of changed file paths.
- Inspect the index and affected maps. Read
docs/features/index.mdand the feature maps for the affected capabilities. Then independently evaluate the applicable area guides loaded on demand, the relevant context glossary for terminology only, and relevant accepted or deferred ADRs. - Update or omit feature maps. Use the
/feature-documentationskill when a map should be created, updated, merged, renamed, or removed. A feature map exists only when it materially helps extend a named capability or exposes a non-obvious ADR constraint. A compact map contains only a short overview and ownership boundary, a## Main Packages and Entry Pointslist that prefers package or feature-module roots (name an individual file only when it is the stable entry point an engineer should open first), and applicable non-obvious ADR links. Omit the map when the change is maintenance-only unless a surviving map became inaccurate — maintenance-only work still requires map link repair when a surviving map points at moved packages or entry points. - Reconcile the domain docs. A guide changes when reusable mechanics or cross-feature boundaries change; a glossary changes only when domain terminology changes. Create or update an ADR only when all three conditions hold: changing the decision would be meaningfully costly, the result is surprising without rationale, and genuine alternatives were considered and traded off. If an implemented ADR-worthy decision lacks reliable evidence of alternatives or rationale, stop and ask the owner; never fabricate a retrospective ADR. Keep glossaries as glossaries.
- Validate documentation. Confirm the feature index is synchronized atomically with every map addition, merge, rename, or removal; package and entry-point links resolve; documentation sits in the right authority; and maps contain no dates, branches, PRs, plans, status, tests, or verification history. Repair package/entry-point links after maintenance refactors even when behavior is unchanged.
What ships with it
5 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 Changed · +53 lines · +33 tokens per session dd8c3deea948
- 1mo ago First seen · 59 lines · 0 tokens per session scan A 4f57176aee2a
finish is a skill published in the GitHub repository sflandergan/agentic-coding (4 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,683 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…