finish

A finishing workflow for a software feature that has already been implemented and reviewed. It records the feature in durable documentation, updates related project terminology and cleans up the work plan.

In plain words
What is it for?
Use it to write a feature reference document, reconcile the glossary and architecture decision records, and close out the feature plan.
Why use it?
It prevents completed work from being left undocumented or inconsistent with the rest of the project.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sflandergan/agentic-coding/finish
Any agent
npx skills add sflandergan/agentic-coding --skill finish
Clone the repo
git clone --depth 1 https://github.com/sflandergan/agentic-coding

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00714
Opus 5 $0.00017 $0.00357
Sonnet 5 $0.00007 $0.00143
Haiku 4.5 $0.00003 $0.00071

Measured 2d ago against content hash 4f57176aee2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

core/claude/skills/finish/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 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: write durable reference documentation, reconcile the domain docs, and clean up the working plan.

Feature (if provided): $ARGUMENTS

Load first

Check git state before doing anything. Then read docs/agents/finish.md and load what it lists. Load the feature spec.md, plan.md, and existing summary.md if present.

Use the feature-documentation skill for writing durable feature docs. Use grill-with-docs only when a domain divergence genuinely needs interrogating.

Subagent usage

Use @explore when finalization depends on repository investigation: implemented code locations, changed routes or jobs, public behavior, git history, or possible domain-language drift. Do not write durable feature docs from weak context; launch an explore subagent with a focused question.

Finish workflow

  1. Confirm done. Confirm the feature is already complete and reviewed. Do not finalize work that is not finished; stop and tell the user what is missing.
  2. Write the feature doc to docs/features/<feature>.md as durable reference documentation — not a status report, implementation diary, or verification log. Use present tense and concrete names (routes, job names, table names, config vars, file paths). Include only the sections that apply, and always include ## Scope and ## Main Code Locations. Do not include: "implemented/ready/reviewed" status, dates, commit hashes, branch/PR names, verification logs, or plan/spec inventories. The doc must be understandable without opening the original plan files.
  3. Reconcile the domain docs (light). If implementation or review changed the domain language or introduced/invalidated a decision, update the relevant docs/contexts/<context>/CONTEXT.md glossary and add or supersede ADRs under docs/adr/. This is reconciliation, not a full grilling session — invoke grill-with-docs only when a divergence genuinely needs interrogating. Keep CONTEXT.md a glossary only.
  4. Clean up by removing plans/<feature-dir>/spec.md and plan.md only after the feature doc is written and the user approves cleanup. Use git rm for tracked files; use plain rm only for untracked paths.
  5. Commit and push. Commit the feature doc and cleanup when the user requests it, then push the current scoped branch with git push origin $(git rev-parse --abbrev-ref HEAD).

Read the full file on GitHub · 59 lines

Changes

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.

  1. 2d ago First seen · 59 lines · 0 tokens per session scan A 4f57176aee2a

Subscribe to this mod's changes

finish is a skill published in the GitHub repository sflandergan/agentic-coding (2 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 714 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens