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 radekamirko/C.R.I.S.P --skill agentgit 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/agent)<a href="https://agentmods.dev/skills/radekamirko/c.r.i.s.p/agent"><img src="https://agentmods.dev/badge/skills/radekamirko/c.r.i.s.p/agent/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/agent"><img src="https://agentmods.dev/badge/skills/radekamirko/c.r.i.s.p/agent.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 | $0.00027 | $0.00828 |
| Opus 5.5 | $0.00011 | $0.00331 |
| Sonnet 5.5 | $0.00005 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
agent-name 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 28d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[Agent Name]
Responsibility
(One paragraph. What is this agent's job? What problem does it solve within the system? What does it own end-to-end?)
Inputs
| # | Input | Type | Source | Required? | Notes |
|---|---|---|---|---|---|
| 1 | string / number / object / array / file | user / API / DB / agent / context | Yes / No | ||
| 2 |
Outputs
| # | Output | Type | Destination | Notes |
|---|---|---|---|---|
| 1 | string / number / object / array | user / API / DB / agent | ||
| 2 |
Boundaries
These are non-negotiable. Claude must follow them every time this agent runs.
This agent must never:
This agent must always:
Human-in-the-loop triggers: (List any output or situation that requires human review before the agent proceeds or commits)
Fallback behavior: (What does this agent do if inputs are incomplete, an API fails, or confidence is low?)
Handoffs
Calls (outbound)
| Agent / Service | When | Input passed | Output expected |
|---|---|---|---|
| (condition that triggers the call) |
Called by (inbound)
| Agent / Trigger | When this agent is invoked | What it receives | What it returns |
|---|---|---|---|
(None — if this agent is standalone)
System Prompt
This is the prompt injected as system context when this agent runs. Edit this carefully — tone, constraints, and framing live here.
You are [agent name], a [role description] for [product name].
Your job: [one sentence description of the core task]
## Context you will receive
[Describe what structured context is passed in — user profile, data snapshot, etc.]
## Your output
[Describe exactly what you return — format, structure, tone]
## Rules
- [Non-negotiable constraint]
- [Non-negotiable constraint]
- [Non-negotiable constraint]
## What you must never do
- [Hard boundary]
- [Hard boundary]
## Tone and language
- [Tone guideline]
- [Language constraint — e.g. "never use medical language"]
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.
- 28d ago First seen · 141 lines · 27 tokens per session scan A 629894ed526b
agent-name is a skill published in the GitHub repository radekamirko/C.R.I.S.P (52 stars, last pushed 29d ago), licensed MIT. It adds 27 tokens to every session and 828 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 2026-09-19.
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'.
procure-to-pay-advisor
Multi-jurisdiction procure-to-pay accounting reference covering PO matching, AP accruals, vendor management, and related compliance.
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…
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…
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…