finalizing-plan

finalizing-plan is a skill for Claude Code from wiolett-industries/marketplace. It costs 56 tokens per session (1,088 once invoked), scanned A, original, MIT.

A final review procedure for completing a planned software task or handoff. It checks the agreed acceptance criteria, fresh verification results, scope, and unresolved serious findings before closing the plan.

In plain words
What is it for?
Use it for standard completion, independent review, risky handoffs, or finalizing an active plan after the implementation and verification work is done.
Why use it?
It reduces the chance of declaring work finished while tests are missing, changes are out of scope, or important problems remain. It also checks that required production UI review and integration evidence are present.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the workflow plugin — 9 skills, 17 agents, 2 hooks shipped together

Good fit Use it for standard completion, independent review, risky handoffs, or finalizing an active plan after the implementation and verification work is done.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wiolett-industries/marketplace/finalizing-plan
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.

Any agent
npx skills add wiolett-industries/marketplace --skill finalizing-plan
Clone the repo
git clone --depth 1 https://github.com/wiolett-industries/marketplace

Made for: Claude Code.

Or install workflow, the plugin that ships this one along with the rest of its 9 skills, 17 agents, 2 hooks.

Wrote 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.

agentmods badge for finalizing-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/wiolett-industries/marketplace/finalizing-plan/github.svg)](https://agentmods.dev/skills/wiolett-industries/marketplace/finalizing-plan)
Your own site
<a href="https://agentmods.dev/skills/wiolett-industries/marketplace/finalizing-plan"><img src="https://agentmods.dev/badge/skills/wiolett-industries/marketplace/finalizing-plan/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.

agentmods 80×15 button for finalizing-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/wiolett-industries/marketplace/finalizing-plan"><img src="https://agentmods.dev/badge/skills/wiolett-industries/marketplace/finalizing-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,088 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00056 $0.01088
Opus 5 $0.00028 $0.00544
Sonnet 5 $0.00011 $0.00218
Haiku 4.5 $0.00006 $0.00109

Measured 10d ago against content hash df6622568abd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

finalizing-plan 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 10d 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.

plugins/workflow/skills/finalizing-plan/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finalizing Plan

Prove the scoped result once, resolve material blockers, close the active plan, and stop. Inherit the existing task-wide assurance, agent, and verification budgets; finalization never creates fresh budgets.

Completion Latch

Completion requires all of the following:

  1. scoped acceptance criteria are satisfied;
  2. required fresh verification is green;
  3. diff/scope sanity finds no silent shrink, unrelated change, or unwired artifact;
  4. no unresolved BLOCKING or HIGH finding remains;
  5. applicable production UI has its ui-contract review and structural reuse evidence;
  6. the active plan is closed with workflow_plan_complete.

Once the latch passes, stop. Do not add another review, rerun unchanged checks, or pursue optional polish.

Inputs And Verification

Read active state, the plan's acceptance criteria, current diff, latest relevant evidence, and only the artifacts needed by the changed paths. For chunked work, finalize local chunk evidence and run one root integration pass; do not create a reviewer matrix per chunk.

Check scope before style: compare the final diff with the reviewed change class, expected surfaces, must-preserve constraints, and non-goals. If material scope or architecture changed, run one new commitment propose/confirm pass; otherwise do not repeat it. Do not turn finalization into architecture polish.

Before accepting a finding that an artifact is missing, stale, or inconsistent, identify its canonical source/owning contract and whether it is generated, mirrored, cached, vendored, synchronized, or runtime-produced. Use one focused project-memory query when durable provenance can change the verdict, then confirm it against current repository, pipeline, or runtime evidence. Reject findings based only on a derived artifact or unresolved provenance.

Use the verification budget from using-workflow:

  • run the strongest relevant targeted bundle once after the final change set;
  • add integration evidence only for actual crossed boundaries;
  • trust a fresh unchanged worker result for its scoped command;
  • repeat a check only after relevant edits, inconclusive evidence, or changed external state.

Read the full file on GitHub · 77 lines

Files

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.

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. 10d ago First seen · 77 lines · 56 tokens per session scan A df6622568abd

Subscribe to this mod's changes

finalizing-plan is a skill published in the GitHub repository wiolett-industries/marketplace (10 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 1,088 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 2026-08-30.

Related

Other skills, from other repositories