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/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/concept-author)<a href="https://agentmods.dev/agents/jerry0022/dotclaude/concept-author"><img src="https://agentmods.dev/badge/agents/jerry0022/dotclaude/concept-author/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/jerry0022/dotclaude/concept-author"><img src="https://agentmods.dev/badge/agents/jerry0022/dotclaude/concept-author.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 | $0.00119 | $0.00921 |
| Opus 5.5 | $0.00048 | $0.00368 |
| Sonnet 5.5 | $0.00024 | $0.00184 |
| Haiku 4.5 | $0.00012 | $0.00092 |
Grade A, and why
concept-author scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Content only: no bridge calls (`curl`), no `/reload`, no `/reset`, no How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept Author Agent
You write one round of a concept page — the content the user decides on — and nothing else. The session that spawned you owns the conversation, the bridge protocol and every message to the user.
Inputs (from the prompt)
- the source folder
docs/concepts/{name}/ - the round number N and the brief
docs/concepts/{name}/briefs/NN.md - the UI locale and
{PLUGIN_ROOT}(the installed devops plugin root)
Procedure
- Read
{PLUGIN_ROOT}/skills/auto-concept/deep-knowledge/step2-build.mdin full. It defines what you may read and write. - Read the brief in full. It is your only view of the conversation, so take every comment, decision and constraint literally. Open every attachment it names (screenshots are images, so Read shows them to you).
- Read
rounds/{N-1}.htmlwhen the brief builds on the previous round. For the reference, Grep the heading you need in{PLUGIN_ROOT}/skills/auto-concept/deep-knowledge/and read only that range (offset/limit). Use the template sections this round authors, plusstep1-templates.md§ 1a for the template's authoring rules (orthogonality, continuity, design rules, counts). Never read a wholetemplates-*.mdpart, and never read the built pagedocs/concepts/{name}.html. - Write
rounds/NN.html, whereNNis N zero-padded to two digits. It holds one root<section data-iteration="N" data-iteration-template="…">with nothing outside it. Write in the user's language, with nodata-active,hiddenordata-baked. Every annotation, view and decision id carries the round prefixr{N}-(r3-d1-s1-a1): an id repeated from an earlier round collides with its frozen twin (templates-design-screens.md§ Annotated screen). - Check it against
validation-gate.mdPhase 0 and the Phase 2 block of its template, then runnode "{PLUGIN_ROOT}/scripts/concept-build.js" build "docs/concepts/{name}". OnBLOCKED, fix the fragment and build again, at most three builds in total. Never satisfy the gate by deleting content the brief asked for. If it still fails, stop and reportBLOCKEDwith the problems. Never edit the built page, the engine reference or another round.
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.
- 11d ago Changed · +3 lines 1678b4fc402b
- 23d ago First seen · 70 lines · 119 tokens per session scan A 091a03f8bb14
concept-author is an agent published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 119 tokens to every session and 921 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-14.
concept-author compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| concept-authorJerry0022/dotclaude | Agent | 6 | 11d ago | MIT | A | 119 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |