review-by-opp:finalize

review-by-opp:finalize is a skill for Claude Code from akshan-main/review-by-opp. It costs 26 tokens per session (586 once invoked), scanned A, original, MIT.

A command that closes a review-by-opp session only after its blocking findings have been resolved and every finding has a recorded outcome. A blocking finding is a problem that prevents approval.

In plain words
What is it for?
Use it as the final check after addressing review findings, to produce a clean or exception-based verdict when the review is eligible to close.
Why use it?
It stops a review from being finalized while serious issues remain open or fixed findings lack explanations. The result is a final verdict based on the recorded review state.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the review-by-opp plugin — 7 skills, 1 hook shipped together

Good fit Use it as the final check after addressing review findings, to produce a clean or exception-based verdict when the review is eligible to close.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/akshan-main/review-by-opp/finalize
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 akshan-main/review-by-opp --skill finalize
Clone the repo
git clone --depth 1 https://github.com/akshan-main/review-by-opp

Made for: Claude Code.

Or install review-by-opp, the plugin that ships this one along with the rest of its 7 skills, 1 hook.

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 review-by-opp:finalize

README.md
[![agentmods](https://agentmods.dev/badge/skills/akshan-main/review-by-opp/finalize/github.svg)](https://agentmods.dev/skills/akshan-main/review-by-opp/finalize)
Your own site
<a href="https://agentmods.dev/skills/akshan-main/review-by-opp/finalize"><img src="https://agentmods.dev/badge/skills/akshan-main/review-by-opp/finalize/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 review-by-opp:finalize

Your own site · 80×15
<a href="https://agentmods.dev/skills/akshan-main/review-by-opp/finalize"><img src="https://agentmods.dev/badge/skills/akshan-main/review-by-opp/finalize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 586 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 $0.00026 $0.00586
Opus 5 $0.00013 $0.00293
Sonnet 5 $0.00005 $0.00117
Haiku 4.5 $0.00003 $0.00059

Measured 10d ago against content hash b9b86f6ea83c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-by-opp:finalize 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.

skills/finalize/SKILL.md · 64 lines

What it actually says

Finalize the review-by-opp session. This is the exit gate.

What to do

  1. Load the ledger:

    • Read reviews/current.json
    • If missing, tell user: "No active session. Run /review-by-opp:start first."
  2. Run the exit gate check: Check ALL of these conditions:

    a. No blocking findings open:

    • Get all findings where status === "open" and severity is in blockingSeverities
    • If any exist: BLOCK. List them and say: "Cannot finalize. {N} blocking finding(s) still open."

    b. No findings without resolution state:

    • Every finding must have a status other than just existing with no decision
    • If any finding has status === "open" and is blocking: BLOCK.

    c. No false completion claims:

    • Any finding marked fixed MUST have a resolution_note
    • If any fixed finding lacks a note: BLOCK. "Finding {id} is marked fixed but has no resolution note."
  3. If blocked:

    • List all blocking reasons
    • Tell user: "Use /review-by-opp:fix to resolve remaining findings."
    • Do NOT finalize.
  4. If clear to finalize:

    • Determine the final verdict:
      • clean - no open findings at all
      • clean_with_accepted_exceptions - only non-blocking findings remain open
      • max_rounds_reached - max rounds hit (but no blocking findings)
    • Set final_verdict in the ledger
    • Write the final state to reviews/current.json
  5. Report final verdict: Show a summary:

    ## Final Verdict: {VERDICT}
    
    - Rounds completed: {N}
    - Total findings: {N}
    - Fixed: {N}
    - Won't fix: {N}
    - Not reproducible: {N}
    - Needs context: {N}
    - Duplicate: {N}
    - Superseded: {N}
    - Still open (non-blocking): {N}
    
  6. Session is now closed. Tell user: "Session finalized. To start a new session, run /review-by-opp:start."

CRITICAL: This is the stop gate. You MUST NOT bypass it. If blocking findings remain, finalization MUST fail. This is the entire point of review-by-opp.

$ARGUMENTS

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 · 64 lines · 26 tokens per session scan A b9b86f6ea83c

Subscribe to this mod's changes

review-by-opp:finalize is a skill published in the GitHub repository akshan-main/review-by-opp (6 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 586 once invoked, about $0.0001 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.