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.
curl -O https://raw.githubusercontent.com/radekamirko/C.R.I.S.P/main/.claude/skills/crisp-orchestrator/SKILL.mdgit clone --depth 1 https://github.com/radekamirko/C.R.I.S.PWrote 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/radekamirko/c.r.i.s.p/crisp-orchestrator)<a href="https://agentmods.dev/skills/radekamirko/c.r.i.s.p/crisp-orchestrator"><img src="https://agentmods.dev/badge/skills/radekamirko/c.r.i.s.p/crisp-orchestrator/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/radekamirko/c.r.i.s.p/crisp-orchestrator"><img src="https://agentmods.dev/badge/skills/radekamirko/c.r.i.s.p/crisp-orchestrator.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 | $0.00073 | $0.01881 |
| Opus 5 | $0.00036 | $0.00941 |
| Sonnet 5 | $0.00015 | $0.00376 |
| Haiku 4.5 | $0.00007 | $0.00188 |
Grade A, and why
crisp-orchestrator 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRISP — Session Orchestrator
Before doing anything else, output this exact text verbatim:
C — Clarify · R — Results · I — Investigate S — Spec · P — Prove · E — Execute
Outcome first. Always.
Step 1: Detect project state
Check if docs/crisp-state.json exists.
If docs/crisp-state.json does NOT exist → Ask what we're starting
Do not assume. Ask:
"Starting fresh — two quick questions:
- Do you have an existing codebase, or are we starting from scratch?
- What's the project?"
If starting from scratch (no existing code):
- Copy
templates/crisp-state.jsontodocs/crisp-state.json, setmode: "discovery" - Read
.claude/skills/phase1-clarify/SKILL.md - Begin Phase C with: "Tell me about the project — what are you trying to solve, or what did the client brief say?"
- Do not explain the methodology. Just ask.
If existing codebase (has code, no docs):
- Copy
templates/crisp-state.jsontodocs/crisp-state.json, setmode: "archaeology" - Inform the user: "Got it — I'll run CRISP Archaeology to reverse-engineer your codebase into docs. This requires the crisp-archaeology skill. Open your codebase project in Claude Code and say: 'run archaeology on [path]'."
- Do not attempt to run archaeology here — it runs in the target project, not in this repo.
If docs/crisp-state.json EXISTS → Read it and route
Read docs/crisp-state.json. Check mode first, then route.
Mode: "discovery" (standard CRISP phases)
1. Report current status
Project: [project.name] · Client: [project.client]
Mode: Discovery
─────────────────────────────────────────
Phases complete: [phases.complete joined with " · " — or "None"]
Current phase: [phases.current]
─────────────────────────────────────────
Summarise the current phase state in 2–3 lines:
- Phase C: "Problem defined as [oneSentence]. Go/No-Go: [goNoGo]. Type: [type]."
- Phase R: "Baseline: [baseline]. Target: [successTarget]. [N] HITL zones defined."
- Phase I: "Process track: [processTrack]. User types: [userTypes]. Data mapping: [dataMappingRequired]."
- Phase S: "[sprintCount] sprints planned. Stack: [stack.layers summary]."
- Phase P: "Outcome: [outcome]."
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 First seen · 196 lines · 73 tokens per session scan A 8c43fc41afea
crisp-orchestrator is a skill published in the GitHub repository radekamirko/C.R.I.S.P (52 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 1,881 once invoked, about $0.0004 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
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'.
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.…
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…
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…
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…
add-educational-comments
Add educational comments to code files to transform them into effective learning resources. Explains the "why" behind syntax, idioms, and design choices, aligned with the learner's knowledge level and educational goals.