C.R.I.S.P: Skill for Claude Code

.claude/skills/crisp-start/SKILL.md

crisp-start is a skill for Claude Code from radekamirko/C.R.I.S.P. It costs 18 tokens per session (194 once invoked), scanned A, original, MIT.

A skill that starts a CRISP product-discovery session by helping define the project problem. CRISP is a step-by-step method covering clarification, results, investigation, specification, proof, and execution.

In plain words
What is it for?
Use it when beginning a new product or AI project and you need to gather the initial brief, clarify the problem, and decide what should happen next.
Why use it?
It provides a consistent starting point for discovery and keeps the conversation focused on the problem before discussing technology.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is radekamirko/C.R.I.S.P's own configuration. It tells Claude Code how to work on C.R.I.S.P itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything C.R.I.S.P configures →

Part of the crisp plugin — 9 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to radekamirko/C.R.I.S.P. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/radekamirko/C.R.I.S.P/main/.claude/skills/crisp-start/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/radekamirko/C.R.I.S.P

Made for: Claude Code.

Or install crisp, the plugin that ships this one along with the rest of its 9 skills.

Wrote 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.

agentmods badge for crisp-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/radekamirko/c.r.i.s.p/crisp-start/github.svg)](https://agentmods.dev/skills/radekamirko/c.r.i.s.p/crisp-start)
Your own site
<a href="https://agentmods.dev/skills/radekamirko/c.r.i.s.p/crisp-start"><img src="https://agentmods.dev/badge/skills/radekamirko/c.r.i.s.p/crisp-start/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.

agentmods 80×15 button for crisp-start

Your own site · 80×15
<a href="https://agentmods.dev/skills/radekamirko/c.r.i.s.p/crisp-start"><img src="https://agentmods.dev/badge/skills/radekamirko/c.r.i.s.p/crisp-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 194 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00194
Opus 5 $0.00009 $0.00097
Sonnet 5 $0.00004 $0.00039
Haiku 4.5 $0.00002 $0.00019

Measured 11d ago against content hash 126848525d0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

crisp-start 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 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.

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.

.claude/skills/crisp-start/SKILL.md · 28 lines

What it actually says

Before doing anything else, output this exact text verbatim:

C — Clarify · R — Results · I — Investigate S — Spec · P — Prove

    Outcome first. Always.

Then read ../phase1-clarify/SKILL.md.

You are beginning a CRISP engagement — Phase C: Clarify.

Rules:

  • Do not explain the methodology.
  • Do not mention phase names, move numbers, or what you're about to do.
  • Do not summarize, narrate, or introduce yourself.
  • Do not talk about technology yet.

After printing the text above, begin with exactly this: "Tell me about the project — what are you trying to solve, or what did the client brief say?"

Then follow ../phase1-clarify/SKILL.md from there.

Changes

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.

  1. 11d ago First seen · 28 lines · 18 tokens per session scan A 126848525d0c

Subscribe to this mod's changes

crisp-start is a skill published in the GitHub repository radekamirko/C.R.I.S.P (52 stars, last pushed 3mo ago), licensed MIT. It adds 18 tokens to every session and 194 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.

Related

Other skills, from other repositories

janitor-discover

Find new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, evaluate a skill URL, check overlap and security risk before installing, or compare a local skill against alternatives. Trigger with '/janitor-discover'.

khendzel/skills-janitor · 58 tokens

procure-to-pay-advisor

Multi-jurisdiction procure-to-pay accounting reference covering PO matching, AP accruals, vendor management, and related compliance.

VincentChuWaiChow/vanguard-frontier-agentic · 32 tokens

alibaba-maestro

Alibaba Cloud Maestro routing skill. Classify the user's Alibaba Cloud task, select the narrowest specialist agent or the right team of specialists from the catalog, and dispatch them — single specialist for focused tasks, parallel team (max 4) for multi-domain tasks. Never auto-dispatch live-guard agents.…

VincentChuWaiChow/vanguard-frontier-agentic · 100 tokens

azure-maestro

Use this skill to classify a user task, select the right Azure specialist agent or team of specialists from the catalog, and dispatch them. Single specialist for focused single-domain tasks; parallel team (max 4) for tasks that span multiple domains. Never auto-dispatches live-guard agents — those always pause for…

VincentChuWaiChow/vanguard-frontier-agentic · 0 tokens

model-registry-refresh

Re-verify and extend catalog/model-registry.json — the fail-closed model-name and reasoning-effort matrix scripts/model-policy.mjs validates against — via delegated Context7-backed research, orchestrator-owned registry edits, and the full validation chain; use when a policy check fails on an unregistered model, a…

VincentChuWaiChow/vanguard-frontier-agentic · 79 tokens

accounting-maestro

Route accounting questions to the narrowest specialist in the catalog. Use when you do not already know the specialist needed. Not for direct accounting answers; Maestro classifies, dispatches, and synthesizes only. Dispatches single agent for focused tasks, parallel team (max 3) for multi-domain tasks. Never…

VincentChuWaiChow/vanguard-frontier-agentic · 93 tokens