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.
npx agentmods add skills/dnlbox/ai-protocol/concept-intakenpx skills add dnlbox/ai-protocol --skill concept-intakegit clone --depth 1 https://github.com/dnlbox/ai-protocolWrote 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/skills/dnlbox/ai-protocol/concept-intake)<a href="https://agentmods.dev/skills/dnlbox/ai-protocol/concept-intake"><img src="https://agentmods.dev/badge/skills/dnlbox/ai-protocol/concept-intake.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00437 |
| Opus 5 | $0.00010 | $0.00218 |
| Sonnet 5 | $0.00004 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
concept-intake 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept intake
Use this skill when the user wants to think aloud about a new project.
Start
- Read
docs/intake/concept-intake.mdwhen it exists. - Resume from the recorded current focus.
- Create
docs/intake/concept-intake.mdwhen it does not exist. - Set a new intake status to
In progress. - Preserve the user's language.
- Interpret speech-to-text errors from context.
- Ask for clarification only when competing interpretations would materially change the concept.
Conversation
- Keep each round focused on one topic.
- Reflect only new or changed meaning.
- Challenge one material weakness when useful.
- Ask at most one next question.
- Ask two questions only when they cannot be separated.
- Avoid administering a questionnaire.
- Avoid turning rough ideas into invented requirements.
- Avoid choosing implementation details.
- Avoid launching research without an explicit request.
Durable intake
- Keep
Working summarycompact. - Keep settled choices in
Decisions. - Keep unresolved matters in
Unknowns. - Keep tangents in
Parking lot. - Track coverage of the user.
- Track coverage of the problem.
- Track coverage of the intended outcome.
- Track coverage of the primary value loop.
- Track coverage of material scope boundaries.
- Track coverage of material risks.
- Track unknowns that must reach concept shaping.
- Record one
Current focus. - Update the intake before replying to a substantive answer.
- Avoid storing a conversation transcript.
Completion
- Recommend completion when the intake covers every required area.
- Recommend completion after two rounds add no new product pillar.
- Allow research questions to carry into concept shaping.
- Complete when the user accepts the recommendation.
- Complete when the user says the intake is sufficient.
- Complete when the user asks to begin concept shaping.
- Reconcile contradictions before completion.
- Remove resolved unknowns before completion.
- Set the status to
Ready for concept shaping. - Return a one-screen readiness summary.
- Stop before editing
docs/concept/.
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.
- 4d ago First seen · 62 lines · 19 tokens per session scan A 53b36c9d1aa2
concept-intake is a skill published in the GitHub repository dnlbox/ai-protocol (19 stars, last pushed 25d ago), licensed MIT. It adds 19 tokens to every session and 437 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ux-writing
Judgment rules for user-facing text and docs: CLI and diagnostic output, error and help text, README and docs structure, code comments, titles, and generated reports, decks, or exports. Use when writing or changing any user-visible string, when adding or restructuring docs or deciding which page owns a fact, when a…
talk-like-scarletkc
按 scarletkc 本人的自然表达习惯撰写、改写、润色和翻译文本，覆盖推文、微博、评论、聊天消息、技术观点、项目介绍、GitHub 文本（README、issue、PR、发布说明）和正式通信。当用户要求用自己的口吻写东西、把 AI 腔文字改自然、发推、回评论、点评模型或开发工具、写项目公告、写礼貌但直接的客服或正式邮件，或要求翻译时保留语气和立场，都使用本 skill，即使用户没有点名 scarletkc 或提出风格要求。.
marketing-copy
Write outbound promotional copy for a product or project: launch and update posts for community platforms and social media, store page descriptions and short blurbs, landing page headlines and calls to action, press-style announcements, and the naming of a product for another language or market. Covers what may be…
scoped-change
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it. Use when scope is ambiguous, a diff touches neighboring surfaces, required dependent edits are unclear, or a proposed compatibility layer, migration, fallback, flag…
agentic-code-review
Use when reviewing a diff, pull request, branch, or AI-generated code for correctness, security, regression, test, performance, and maintainability risks before merge.
hooksmith
Use when designing or reviewing safe Grok Build hooks for linting, tests, formatting, notifications, command guards, lifecycle automation, or project hook trust decisions.