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 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/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/skills/dnlbox/ai-protocol/concept-intake"><img src="https://agentmods.dev/badge/skills/dnlbox/ai-protocol/concept-intake.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 | $0.00019 | $0.00437 |
| Opus 5.5 | $0.00008 | $0.00175 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 2mo ago), licensed MIT. It adds 19 tokens to every session and 437 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 2026-08-30.
Other skills, from other repositories
managing-mcp-servers
Use when the user asks to add, change, remove, enable or disable an MCP server, or when an MCP tool is missing, needs sign-in, fails, or was blocked. ThinkRail runs pi in-process, so there is no pi command to call.
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
animate
Build a web animation: whether it should animate at all, the purpose, the tool, the properties, the easing curve, the duration, interruption and exit. Writes the CSS or Motion code for dropdowns, modals, toasts, tooltips, accordions, press feedback, stagger and scroll reveals. Use to animate something or make a…
postgresdb
Use when PostgreSQL engine behaviour decides the answer — schema and type design, index choice, reading EXPLAIN on a slow query, zero-downtime DDL and backfills, or ops (roles, RLS, pooling, vacuum, partitioning, PITR). PG16, ORM-agnostic. NOT portable query logic (that is sql), NOT a managed provider's platform…