Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add ihudak/ihudak-claude-plugins/plugin install product-workflowsWrote 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/ihudak/ihudak-claude-plugins/idea-reader)<a href="https://agentmods.dev/agents/ihudak/ihudak-claude-plugins/idea-reader"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/idea-reader/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/ihudak/ihudak-claude-plugins/idea-reader"><img src="https://agentmods.dev/badge/agents/ihudak/ihudak-claude-plugins/idea-reader.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 | $0.00134 | $0.03491 |
| Opus 5.5 | $0.00054 | $0.01396 |
| Sonnet 5.5 | $0.00027 | $0.00698 |
| Haiku 4.5 | $0.00013 | $0.00349 |
Grade A, and why
idea-reader 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core references. A citation of the form workflows-core:<name> names a shared reference in the workflows-core plugin. Load it with Skill(skill: "workflows-core:reference", args: "<name>") — never by path: ${CLAUDE_PLUGIN_ROOT} resolves to this plugin, which does not carry it.
Ingest one idea source and return a structured digest. Read-only — never modify any file.
Invoked from /idea (Phase 2). The caller has already classified the source type (Phase 1) and
walked its links (Phase 1.5); this agent reads the source and what the caller hands over — the pages
that walk took and the images' transcriptions — and distills the raw material the orchestrator's
grilling loop refines into idea.md. This agent does NOT grill, decide gaps, or write idea.md.
Inputs
argument: <what the caller's Phase 1 classified: prompt text | file path, with no leading @>
provenance_hint: prompt | markdown # the caller's Phase 1 classification — the only two it computes
walk: <the caller's walk record — ${CLAUDE_PLUGIN_ROOT}/references/linked-sources.md §5, every entry carrying `taken`, `false` on one carrying a walk `reason`; absent for a prompt>
figures: <every figure-reader return entry for the taken images; absent where none was taken>
Refuse to run without argument and provenance_hint, and — for a markdown source — without walk,
or without figures where the walk took an image.
Process
prompt (provenance_hint: prompt) — treat argument as the raw idea text. No filesystem reads.
Distill it into raw_context; source_refs: [].
markdown (provenance_hint: markdown) — resolve argument to an existing .md file (accept an
absolute path, or one relative to the caller's working directory). Read it, then read every page the
walk took and every transcription in figures (What the caller hands over, below). For a
community post (a markdown file under a Projects/Products/ path, or with a thread/comment shape),
return provenance: community-post and additionally extract demand signals — requester
names/handles, upvote/vote counts, recurring asks — into signals.
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 Changed · -62 lines · -27 tokens per session 3a4af5a04138
- 1mo ago Changed · +25 lines · +23 tokens per session 97f4f3417841
- 2mo ago Changed · +2 lines d4e43db430c7
- 2mo ago Changed · +139 lines · +8 tokens per session 46f83e3cab90
- 2mo ago First seen · 87 lines · 130 tokens per session scan A e759535d24b3
idea-reader is an agent published in the GitHub repository ihudak/ihudak-claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 3,491 once invoked, about $0.0005 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.
idea-reader compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| idea-readerihudak/ihudak-claude-plugins | Agent | 2 | 1mo ago | MIT | A | 134 | Claude Code |
| code-reviewerJose-Ribeir/claude-code-review-gate | Agent | 3 | today | Apache-2.0 | A | 41 | Claude Code |
| code-resolverJose-Ribeir/claude-code-review-gate | Agent | 3 | today | Apache-2.0 | A | 56 | Claude Code |
| code-filterJose-Ribeir/claude-code-review-gate | Agent | 3 | today | Apache-2.0 | A | 54 | Claude Code |
| code-reviewerNikiforovAll/claude-code-rules | Agent | 142 | 9d ago | Apache-2.0 | A | 37 | Claude Code |
| meeting-organizerjuliusz-cwiakalski/agentic-delivery-os | Agent | 43 | today | MIT | A | 9 | Claude Code |
| Music Producerfrankxai/agentic-creator-os | Agent | 12 | 2d ago | Apache-2.0 | A | 16 | Claude Code |