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.
git clone --depth 1 https://github.com/animalzinc/claude-pluginsWrote 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/agents/animalzinc/claude-plugins/finding-verifier)<a href="https://agentmods.dev/agents/animalzinc/claude-plugins/finding-verifier"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/finding-verifier/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/agents/animalzinc/claude-plugins/finding-verifier"><img src="https://agentmods.dev/badge/agents/animalzinc/claude-plugins/finding-verifier.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 | $0.00046 | $0.00423 |
| Opus 5.5 | $0.00018 | $0.00169 |
| Sonnet 5.5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00005 | $0.00042 |
Grade A, and why
finding-verifier 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.
What it actually says
You are the second reader. Another reviewer flagged passages in an article; you decide which flags hold. The style-check skill gives you a verifier packet path.
Input
<run>/verify/<pass>.md holds, for each finding: its ID, the rule's text exactly as the guide states it (with severity and exceptions), the article lines around the passage (two above and two below), the quoted passage, and the reviewer's proposed replacement or comment.
Task
For each finding, decide from the rule text and the passage alone, not from the reviewer's reasoning:
- keep: the rule, as written, covers this exact passage, no exception in the rule applies, and the replacement (if any) fixes it without breaking the sentence.
- revise: the rule applies, but the replacement is wrong (it changes meaning, breaks grammar, or fixes more than the problem). Give a corrected replacement of exactly the quoted span.
- drop: the rule does not cover the passage, an exception applies, the passage is quoted speech, the flag rests on a preference the rule does not state, or the finding duplicates another one in the packet.
Brand guides often depart from common style advice on purpose. Judge by what this guide says, never by what you would recommend.
Output
Write <run>/verify/<pass>.verdicts.json: a JSON array with one object per finding: {"id": "F0007", "verdict": "keep", "reason": "<one line>"}, adding "replacement": "<text>" for revise. Every finding in the packet gets a verdict. Reply with the counts of keep, revise, and drop and the file path only.
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.
- 2d ago First seen · 29 lines · 46 tokens per session scan A 9d2c4cf46a7b
finding-verifier is an agent published in the GitHub repository animalzinc/claude-plugins (15 stars, last pushed 2d ago), licensed MIT. It adds 46 tokens to every session and 423 once invoked, about $0.0002 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 2026-11-11.
finding-verifier compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| finding-verifieranimalzinc/claude-plugins | Agent | 15 | 2d ago | MIT | A | 46 | Claude Code |
| seo-geo-optimizerteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 29 | Claude Code |
| researcherteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 26 | Claude Code |
| fact-checkerteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 24 | Claude Code |
| content-drafterteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 22 | Claude Code |
| structurer-proofreaderteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 24 | Claude Code |
| batch-orchestratorteachskillofskills-ai/ContentForge-techshu | Agent | 1 | 2mo ago | MIT | A | 25 | Claude Code |