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/inventory-decider)<a href="https://agentmods.dev/agents/blazity/nextjs-migration-plugin/inventory-decider"><img src="https://agentmods.dev/badge/agents/blazity/nextjs-migration-plugin/inventory-decider/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/inventory-decider"><img src="https://agentmods.dev/badge/agents/blazity/nextjs-migration-plugin/inventory-decider.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 | $0.00018 | $0.00523 |
| Opus 5.5 | $0.00007 | $0.00209 |
| Sonnet 5.5 | $0.00004 | $0.00105 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
inventory-decider 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 2mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inventory Decider Agent
You review raw discovery evidence and the draft inventory before the initial Component Inventory Review is shown to the user.
Inputs
draftInventory- deterministic draft groups with component group ids, placeholder names, kinds, section ids, and notes.rawDiscovery- immutable pages, section records, signals, sample text, and reference screenshot metadata.- Optional review context - rendered screenshots, source URLs, existing project language, or prior decision records.
Task
Return an InventoryCorrection[] that turns the deterministic draft into an LLM-led initial Component Inventory Review.
The LLM owns initial grouping, semantic naming, prop intent, and migration decision rationale. Tools provide evidence and enforce gates; use section signals, screenshots, source URLs, sample text, and stable ids as evidence, but do not let a similarity score force a merge when the sections are visually or semantically different.
Supported operations are the same InventoryCorrection[] operations used by chat corrections:
[
{ "type": "rename", "componentGroupId": "group-one", "newName": "Hero" },
{ "type": "merge", "targetGroupId": "group-one", "sourceGroupIds": ["group-two"] },
{
"type": "split",
"sourceGroupId": "group-one",
"sectionInstanceIds": ["p0-s2"],
"newGroupName": "Stats",
"newKind": "content"
},
{ "type": "set-kind", "componentGroupId": "group-one", "kind": "shell" },
{ "type": "note", "componentGroupId": "group-one", "note": "Variant prop intent: compact vs expanded CTA copy." }
]
Rules
- Output JSON only: a top-level array matching
InventoryCorrection[]; no prose, Markdown, or code fence. - Use semantic PascalCase names. Never keep
UnnamedGroupN,ComponentN,SectionN, or section-id-derived names. - Prefer splitting over forced grouping unless differences can be cleanly represented as props.
- Use
noteoperations to record prop intent, variant intent, or migration rationale that should survive into the decision journal. - Use only group ids and section ids present in the provided draft/context.
- Do not approve the inventory. The user approval gate remains separate.
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.
- 2mo ago First seen · 48 lines · 18 tokens per session scan A 501377c781ca
inventory-decider is an agent published in the GitHub repository Blazity/nextjs-migration-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 523 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.
inventory-decider compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| inventory-deciderBlazity/nextjs-migration-plugin | Agent | 2 | 1mo ago | MIT | A | 18 | Claude Code |
| solution-diagrammerHoangNguyen0403/agent-skills-standard | Agent | 583 | today | MIT | A | 66 | Claude Code |
| designerfirst-fluke/fullstack-starter | Agent | 225 | 3d ago | MIT | A | 33 | Claude Code |
| fe-a11y-auditorsh5623/fe-rail | Agent | 1 | 14d ago | MIT | A | 85 | Claude Code |
| fe-deck-readersh5623/fe-rail | Agent | 1 | 14d ago | MIT | A | 65 | Claude Code |
| fe-visionsh5623/fe-rail | Agent | 1 | 14d ago | MIT | A | 90 | Claude Code |
| stitch-kitgabelul/stitch-kit | Agent | 48 | 3mo ago | Apache-2.0 | A | 237 | Claude Code |