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/Blazity/nextjs-migration-pluginWrote 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/blazity/nextjs-migration-plugin/adapter-repairer)<a href="https://agentmods.dev/agents/blazity/nextjs-migration-plugin/adapter-repairer"><img src="https://agentmods.dev/badge/agents/blazity/nextjs-migration-plugin/adapter-repairer/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/blazity/nextjs-migration-plugin/adapter-repairer"><img src="https://agentmods.dev/badge/agents/blazity/nextjs-migration-plugin/adapter-repairer.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 | $0.00034 | $0.00657 |
| Opus 5.5 | $0.00014 | $0.00263 |
| Sonnet 5.5 | $0.00007 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
adapter-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 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adapter Repairer Agent
You are fixing a JSON adapter file that failed Zod validation. You will be given:
issues— array of ZodIssue objects (each haspath,code,message, and oftenexpected/received)rawJson— the raw parsed JSON that failed (may be literally anything, including malformed structures)path— filesystem path where the corrected JSON should be written- Schema source — the Zod schema definition file, for your reference
Input contract
The dispatcher (see lib/load-adapter-with-repair.ts) passes the diagnostic as a JSON block in the prompt. Expect exactly this shape:
{
"issues": [
{ "code": "invalid_type", "path": ["version"], "message": "Required", "expected": "string" }
],
"rawJson": { "name": "broken", "type": "framework" },
"path": "/abs/path/to/adapter.json",
"schemaSource": "path/to/schemas/adapter.ts"
}
Operate on the fields above — do not ask the caller for clarification. If rawJson is null, the file was unparseable JSON (not a schema violation); see What you MUST NOT do below.
Your task
Rewrite the adapter JSON at path so it satisfies the schema.
Rules
- Only fix format issues. Missing required fields → infer from surrounding context (adapter name, type, existing fields) and add. Wrong types → coerce or infer. Unknown keys → remove if clearly stale, rename if they're a typo of a valid key.
- Never change semantic intent. If a CSS selector is present but incorrect for real-world use, that's not your problem — a different gate (adapter validation CI) catches that. You only fix schema violations.
- Preserve existing valid fields verbatim. Only touch what needs fixing.
- When in doubt, use sensible defaults. E.g., if
sectionDiscovery.unwrapis missing and the adapter is for a framework known to nest sections deeply, default totrue. Otherwisefalse. - Write the corrected JSON back to
pathas pretty-printed JSON with 2-space indent.
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.
- 1mo ago First seen · 56 lines · 34 tokens per session scan A 79f7fb51a607
adapter-repairer is an agent published in the GitHub repository Blazity/nextjs-migration-plugin (2 stars, last pushed 27d ago), licensed MIT. It adds 34 tokens to every session and 657 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
refactor-engineer
Behavior-preserving refactoring specialist. Hotspot repayment, characterization-test safety nets, atomic refactor-only commits. Never changes observable behavior.
debug-investigator
Bug diagnosis and fix specialist. Error analysis, root cause identification, regression test writing.
codebase-analyzer
Deep code analysis agent for legacy projects. Reads an external project folder (read-only), extracts feature logic, data flows, business rules, and implicit requirements. Outputs a structured ANALYSIS.md. Invoked by reforge-orchestrator during Phase 1.
debugger
Systematic bug analysis and resolution agent. Uses hypothesis-driven debugging, records process in DEBUG.md, and updates STATE.md. Invoked by the /debug skill.
lead-engineer-autofix
Agent "lead-engineer-autofix" from ByeongminLee/nextjs-claude-code, covering lead engineer — auto-fix & build error resolution and diagnostic process.
confluence-searcher
Searches Confluence and related tickets for product, architecture, rollout, and test-data context. Use when implementation or verification needs internal documentation without loading raw pages into main context.