state-repairer

An agent that repairs JSON state files after they fail validation against a Zod schema, a set of rules describing valid data. It fixes formatting and type problems while preserving valid information.

In plain words
What is it for?
Use it to repair files such as crawl.json or probe.json, correct wrong data types and obvious typos, fill schema-required defaults, and remove unknown fields.
Why use it?
It helps a crawling workflow recover from malformed or incorrectly shaped state data without deleting the file or inventing unnecessary content.

Agent

Part of the nextjs-migration-plugin plugin — 18 skills, 4 commands, 15 agents shipped together

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.

agentmods
npx agentmods add agents/blazity/nextjs-migration-plugin/state-repairer
Clone the repo
git clone --depth 1 https://github.com/Blazity/nextjs-migration-plugin

Or install nextjs-migration-plugin, the plugin that ships this one along with the rest of its 18 skills, 4 commands, 15 agents.

Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.00449
Opus 5 $0.00028 $0.00225
Sonnet 5 $0.00011 $0.00090
Haiku 4.5 $0.00006 $0.00045

Measured 2d ago against content hash 968ba0c107d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

state-repairer 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.

agents/state-repairer.md · 43 lines

What it actually says

State Repairer Agent

You are fixing a JSON state file that failed Zod validation.

Input contract

The dispatcher (see lib/load-with-repair.ts) passes the diagnostic as a JSON block in the prompt. Expect this shape:

{
  "issues": [
    { "code": "invalid_type", "path": ["pages", 0, "depth"], "message": "Expected number, received string" }
  ],
  "rawJson": { "pages": [{ "url": "https://...", "depth": "zero" }] },
  "path": "/abs/path/to/state.json",
  "schemaSource": "schemas/<name>.ts"
}

If rawJson is null, the file was unparseable JSON; do not invent content from scratch — re-emit the closest plausible valid skeleton based on the schema, but flag the loss in your output summary.

Your task

Rewrite the JSON at path so it satisfies the schema. Pretty-print with 2-space indent. Append a one-line summary of what you changed.

Rules

  1. Format only. Coerce types, fill required fields with defaults from the schema (or sensible inferences from sibling fields), drop unknown keys, rename obvious typos.
  2. Preserve all valid data. Only touch what the issues array points at, plus dependent fields the schema mandates.
  3. Never delete the file.
  4. Never write to any other path.

What you MUST NOT do

  • Do not modify the schema file
  • Do not invent data not present in rawJson unless the schema forces a default
  • Do not auto-repair semantic errors (e.g., a recommendation of ABORT_NO_ADAPTER for a page the user wanted extracted) — those are the calling phase's concern
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. 2d ago First seen · 43 lines · 57 tokens per session scan A 968ba0c107d0

Subscribe to this mod's changes

state-repairer is an agent published in the GitHub repository Blazity/nextjs-migration-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 449 once invoked, about $0.0003 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.

Related

Other agents, from other repositories

claudemd-maintainer

Use right after any substantive repo change to keep CLAUDE.md accurate. Re-reads the changed files and updates the file inventory, the data-driven content table, architecture notes, and the commands section so every claim matches reality. Read-only except for CLAUDE.md.

roshantaneja/roshantaneja.github.io · 61 tokens

rot-sweeper

Use after a change to remove what it deprecated — now-unused npm dependencies, orphaned files/components/styles, dead exports, stale config/scripts. Verifies references across ALL file types and confirms the build passes before declaring done. Surfaces untracked/unrecoverable or load-bearing deletions for human…

roshantaneja/roshantaneja.github.io · 70 tokens

docs-syncer

Use after a change to sync the human-facing docs — README.md, data/ADDINGCONTENT.md, and affected code comments/inline docstrings — with the new reality. Leaves CLAUDE.md to claudemd-maintainer.

roshantaneja/roshantaneja.github.io · 50 tokens

merge-conflict-resolver

Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…

module-federation/core · 264 tokens

database-engineer

PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.

yonatangross/orchestkit · 28 tokens

ts-coder

Use this agent when you need to write or refactor TypeScript code following strict type safety and simplicity principles. This includes creating type definitions, implementing business logic, refactoring JavaScript to TypeScript, or optimizing type inference.

giselles-ai/giselle · 49 tokens