verify-findings

verify-findings is a skill for Claude Code from closedloop-ai/claude-plugins. It costs 171 tokens per session (1,790 once invoked), scanned A, original, Apache-2.0.

A code-review step that sends each reported issue to a separate checker trained to look for evidence that the issue is wrong.

In plain words
What is it for?
It helps verify findings in local or GitHub-based code-review workflows, using separate checker tasks for each eligible finding.
Why use it?
It reduces false alarms by giving findings an independent challenge before they are shown as verified. It also records rejected findings so people can review those decisions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the code-review plugin — 5 skills, 4 commands, 2 agents shipped together

Good fit It helps verify findings in local or GitHub-based code-review workflows, using separate checker tasks for each eligible finding.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/closedloop-ai/claude-plugins/verify-findings
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 closedloop-ai/claude-plugins --skill verify-findings
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code.

Or install code-review, the plugin that ships this one along with the rest of its 5 skills, 4 commands, 2 agents.

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 verify-findings

README.md
[![agentmods](https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/verify-findings/github.svg)](https://agentmods.dev/skills/closedloop-ai/claude-plugins/verify-findings)
Your own site
<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/verify-findings"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/verify-findings/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 verify-findings

Your own site · 80×15
<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/verify-findings"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/verify-findings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,790 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 3
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
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 $0.00171 $0.01790
Opus 5.5 $0.00068 $0.00716
Sonnet 5.5 $0.00034 $0.00358
Haiku 4.5 $0.00017 $0.00179

Measured 1mo ago against content hash 4ada906fcb94, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-findings 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.

plugins/code-review/skills/verify-findings/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Finding-Verifier Fleet Dispatch (stage_23_verify_findings)

This skill is the canonical finding-verifier dispatcher for /code-review at stage_23_verify_findings. It is split out of commands/start.md so the orchestration spine stays lean; the orchestrator invokes it when the walker reaches stage_23_verify_findings. The content below is authoritative for both MODE=local and MODE=github, with mode-specific Task scheduling: GitHub mode dispatches verifiers synchronously, while local mode preserves parallel background dispatch plus blocking TaskOutput collection.


Verifier Fleet (stage_23_verify_findings)

This stage runs when the walker reaches stage_23. It implements PLN-722's finding-verification pass: each eligible finding gets an independent second opinion from a verifier agent prompted to falsify (not confirm) the original claim. Findings that survive land in verified[]; findings rejected with positive evidence land in rejected[] and surface in the "Dismissed Findings" section so humans can falsify the dismissal.

Inputs

stage_22b_verify_prepare already wrote <CR_DIR>/verify_manifest.json and one input file per eligible finding at <CR_DIR>/verifier_inputs/<finding_id>.json. Read the manifest:

{
  "to_verify": [{"finding_id", "model", "input_path", "output_path", ...}, ...],
  "skipped_no_verification": [...],
  "deferred_budget": [...],
  "cache_hits": [...]
}

cache_hits[] entries have already been materialized at their output_path; do NOT respawn them. Only entries in to_verify[] need fleet dispatch.

If verify_manifest.json is absent, do NOT dispatch any verifier — stop and report. stage_22b_verify_prepare writes it last and exits 3 without it when it could not prove the review root, so a missing manifest means the verifiers would resolve source paths against a tree that is not the one under review.

Spawn contract

First branch on MODE. GitHub and local runs intentionally use different Task scheduling because GitHub headless mode cannot survive outstanding background verifiers after the assistant turn ends.

Read the full file on GitHub · 73 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. 1mo ago Changed · +2 lines 4ada906fcb94
  2. 1mo ago First seen · 71 lines · 171 tokens per session scan A 499dee069f3b

Subscribe to this mod's changes

verify-findings is a skill published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed today), licensed Apache-2.0. It adds 171 tokens to every session and 1,790 once invoked, about $0.0007 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 2026-08-30.