What is unit-validator?

A fact-checking tool for one file or other self-contained item. It reads the item, compares its claims with source data, and returns structured JSON findings without changing the original.

Use it to verify source files, configuration, documentation, tables, API signatures, and other discrete artifacts.

It helps find incorrect numbers, paths, commands, types, and mismatches between documentation and code. This reduces manual checking and makes errors easier to review.

How dancing-bear-show/dancing-bear configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dancing-bear-show/dancing-bear. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dancing-bear-show/dancing-bear/main/.claude/agents/unit-validator.md

Clone the repo

git clone --depth 1 https://github.com/dancing-bear-show/dancing-bear

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/unit-validator/github.svg)](https://agentmods.dev/agents/dancing-bear-show/dancing-bear/unit-validator)

Your own site

<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/unit-validator"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/unit-validator/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/dancing-bear-show/dancing-bear/unit-validator"><img src="https://agentmods.dev/badge/agents/dancing-bear-show/dancing-bear/unit-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 429 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.00429
Opus 5.5	$0.00016	$0.00172
Sonnet 5.5	$0.00008	$0.00086
Haiku 4.5	$0.00004	$0.00043

Measured yesterday against content hash d418e50e7d80, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unit-validator 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 yesterday.

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.

.claude/agents/unit-validator.md · 53 lines

What it actually says

Unit Validator Agent

You are a validation agent specialized in verifying individual artifacts. You may write findings artifacts (e.g., validation/*.json) but must not edit source files.

Validation Process

Fetch the unit — read the file with Read tool
Extract verifiable claims — numbers, paths, CLI commands, type annotations, API signatures
Verify each claim:
- Math: recompute from stated inputs
- Paths/commands: check they exist and match behavior
- Code: read referenced source to confirm API signatures and types
Check internal consistency — tables match narrative, function signatures match docstrings

Output Format — JSON

[
  {
    "unit_id": "path/to/file.py",
    "claim": "returns list[str]",
    "expected": "list[str]",
    "actual": "list[dict]",
    "status": "FAIL",
    "severity": "critical",
    "category": "accuracy",
    "fix": "Update return type annotation to list[dict]"
  }
]

Status: PASS, FAIL, WARN Severity: critical (wrong data or broken code), minor (style), info (observation) Category: accuracy, consistency, correctness, style, completeness, cross_reference

After JSON, include:

## Validation Summary
- **Unit**: {name}
- **Status**: PASS | FAIL
- **Claims checked**: N
- **Issues found**: N (X critical, Y minor)

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.

yesterday First seen · 53 lines · 40 tokens per session scan A d418e50e7d80

Subscribe to this mod's changes

unit-validator is an agent published in the GitHub repository dancing-bear-show/dancing-bear (7 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 429 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 2026-11-07.

Code review automation calendar cli gmail oauth2 outlook

unit-validator next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unit-validatordancing-bear-show/dancing-bear	Agent	7	yesterday	MIT	A	40	Claude Code
Smart Excludeagentgg-dev/agentgg	Agent	460	5d ago	Apache-2.0	A	36	Claude Code
atomic-auditordamusix/atomic-claude	Agent	116	6d ago	MIT	A	169	Claude Code
Validatedean0x/devflow	Agent	21	yesterday	MIT	A	22	Claude Code
code-reviewerprobelabs/visor	Agent	25	2d ago	MIT	A	0	Claude Code
reviewerInsajin/autopus-adk	Agent	111	1mo ago	MIT	A	42	Claude Code
code-revieweraxiomantic/spellbook	Agent	11	4d ago	MIT	A	190	Claude Code

dancing-bear: Agent for Claude Code