chunk-validator

chunk-validator is an agent for Claude Code from drobins25/craft. It costs 211 tokens per session (4,821 once invoked), scanned A, original, MIT.

A validation agent that checks changed project work and reports the results.

In plain words
What is it for?
It is for running type checks, linting, checks for unsafe any types, builds, tests, and design-token checks in per-chunk or final-story modes.
Why use it?
It gives the orchestrator a consistent report on problems found by code checks without changing the project itself.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the craft plugin — 11 skills, 36 commands, 27 agents, 7 hooks, 1 MCP server shipped together

Good fit It is for running type checks, linting, checks for unsafe any types, builds, tests, and design-token checks in per-chunk or final-story modes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/drobins25/craft/chunk-validator
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.

Clone the repo
git clone --depth 1 https://github.com/drobins25/craft

Made for: Claude Code.

Or install craft, the plugin that ships this one along with the rest of its 11 skills, 36 commands, 27 agents, 7 hooks, 1 MCP server.

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 chunk-validator

README.md
[![agentmods](https://agentmods.dev/badge/agents/drobins25/craft/chunk-validator/github.svg)](https://agentmods.dev/agents/drobins25/craft/chunk-validator)
Your own site
<a href="https://agentmods.dev/agents/drobins25/craft/chunk-validator"><img src="https://agentmods.dev/badge/agents/drobins25/craft/chunk-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.

agentmods 80×15 button for chunk-validator

Your own site · 80×15
<a href="https://agentmods.dev/agents/drobins25/craft/chunk-validator"><img src="https://agentmods.dev/badge/agents/drobins25/craft/chunk-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 211 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,821 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 $0.00211 $0.04821
Opus 5.5 $0.00084 $0.01928
Sonnet 5.5 $0.00042 $0.00964
Haiku 4.5 $0.00021 $0.00482

Measured 14d ago against content hash 8962cf4f3ae2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chunk-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 14d 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.

agents/chunk-validator.md · 331 lines

How it starts

The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chunk Validator

You are a validation executor. You run quality checks against a project and return a structured report. You do NOT fix issues — you report them. The orchestrator decides what to do with failures.

Input

You receive these values in your prompt:

  • CHUNK: "N/total: title" (e.g., "2/4: API routes") or "final" for story-final mode
  • FILES_CHANGED: comma-separated file paths the chunk touched
  • PROJECT_ROOT: absolute path to the project root
  • PM: package manager (pnpm/npm/yarn/bun)
  • STORY_FILE: absolute path to the story markdown file
  • MODE: "per-chunk" or "story-final" (derived from CHUNK value: if CHUNK is "final" then story-final, otherwise per-chunk)
  • PLUGIN_ROOT: absolute path to the craft plugin root (locates plugin-internal scripts like gate-signals.sh). If absent from your prompt, the Gates row reports coverage unknown (no probe) — never guess the path.

Mode Detection

Determine the validation mode from the CHUNK value:

  • If CHUNK is "final" → story-final mode — run ALL checks at maximum strictness
  • Otherwise (CHUNK is "N/total: title") → per-chunk mode — skip Build and Tests (they run at story-final)

This is separate from Graduated Severity. Mode determines WHICH checks run. Severity determines WARN vs FAIL for checks that DO run.

Graduated Severity

Parse the CHUNK value to determine chunk position:

  • Extract N and total from "N/total: title" format
  • Final chunk (N == total) or story-final ("final"): ALL failures are FAIL
  • Non-final chunk (N < total): lint and any-types failures are WARN, everything else is FAIL

WARN means the issue is logged but does NOT block completion. FAIL means the issue blocks completion.

Pre-Check: Read quality.yaml and package.json, scan stack signals

Before running any checks, read TWO files using the Read tool and run ONE Bash call:

  1. PROJECT_ROOT/.craft/quality.yaml — If this file exists, parse the gates: section. Each gate has an enabled: field (true/false). If a gate is enabled: false, SKIP that check entirely. Map gate names to checks:
    • gates.typecheck.enabled → TypeScript Strict (check 1)
    • gates.lint.enabled → Lint (check 2)
    • gates.build.enabled → Build (check 4)
    • gates.tests.enabled → Tests + Coverage (check 5)
    • No Any Types (check 3) and Design Tokens (check 6) are always enabled — they have no gate.

Read the full file on GitHub · 331 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. 14d ago Changed · +2 lines 8962cf4f3ae2
  2. 2mo ago First seen · 329 lines · 211 tokens per session scan A c9ab9ce782e0

Subscribe to this mod's changes

chunk-validator is an agent published in the GitHub repository drobins25/craft (73 stars, last pushed yesterday), licensed MIT. It adds 211 tokens to every session and 4,821 once invoked, about $0.0008 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.

Related

chunk-validator compared with agents from other repositories

chunk-validator next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
chunk-validatordrobins25/craftAgent73yesterdayMITA211Claude Code
performance-tuneralirezarezvani/claude-code-tresorAgent7824mo agoMITA30Claude Code
docs-writeralirezarezvani/claude-code-tresorAgent7824mo agoMITA33Claude Code
systems-architectalirezarezvani/claude-code-tresorAgent7824mo agoMITA33Claude Code
config-safety-revieweralirezarezvani/claude-code-tresorAgent7824mo agoMITA37Claude Code
unity-optimizerXeldarAlz/everything-claude-unityAgent256mo agoMITA46Claude Code
unity-prototyperXeldarAlz/everything-claude-unityAgent256mo agoMITA52Claude Code