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/hannesill/m4/create-m4-skillnpx skills add hannesill/m4 --skill create-m4-skillgit clone --depth 1 https://github.com/hannesill/m4Wrote 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/hannesill/m4/create-m4-skill)<a href="https://agentmods.dev/skills/hannesill/m4/create-m4-skill"><img src="https://agentmods.dev/badge/skills/hannesill/m4/create-m4-skill.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 5.1 | $0.00052 | $0.02018 |
| Opus 5 | $0.00026 | $0.01009 |
| Sonnet 5 | $0.00010 | $0.00404 |
| Haiku 4.5 | $0.00005 | $0.00202 |
Grade A, and why
create-m4-skill 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 6d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
M4 Skill Creator
This skill guides you through creating properly formatted M4 skills with complete provenance tracking and appropriate tier and category assignment.
When to Use This Skill
- User asks to create a new M4 skill
- User wants to document a clinical scoring system, cohort definition, or research pattern
- User wants to document an M4 framework feature or workflow
- User mentions "new skill", "create skill", "document [concept]"
- User wants to contribute to the M4 skills library
Interactive Creation Process
Follow these steps in order. At each step, gather information from the contributor and validate completeness before proceeding.
Step 1: Understanding the Skill
Interview the contributor with these questions:
- What concept does this skill address?
- Is this a clinical skill (scoring system, cohort definition, lab interpretation, medication calculation) or a system skill (M4 framework feature, data structure, workflow pattern)?
- When should an AI assistant activate this skill? (Specific triggers)
- Is this based on:
- Published source code (e.g., MIT-LCP mimic-code)?
- Original domain expertise?
- Community contribution?
- What are the key references? (Publications for clinical, documentation/repos for system)
Do NOT auto-generate answers. Wait for contributor input at each question.
Step 2: Determine Category and Tier
Based on their answers, assign category and guide tier selection:
Category (from question 2):
clinical— Encodes clinical domain knowledgesystem— Encodes M4 framework knowledge, data structure guidance, or meta-skills
Tier selection for clinical skills:
validated— Derives from published, validated source (mimic-code, peer-reviewed paper). Has URL to source. Will be reviewed by at least one clinician for clinical accuracy.expert— Original work by a clinician or domain expert. Will be reviewed by at least one independent clinician. Creator has clinical expertise.community— Contribution without required clinical reviews. Technical review for correctness.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 241 lines · 52 tokens per session scan A 3e5c5c9196fe
create-m4-skill is a skill published in the GitHub repository hannesill/m4 (43 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 2,018 once invoked, about $0.0003 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
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
autogpt-agents
Autonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or building complex multi-step AI automation systems.
arbor-research-agent
Public entrypoint for the Arbor skill suite. Use when a user wants to run an Arbor-style autonomous research or optimization workflow from a natural-language goal, including initial clarification of objective, target project, data, metric, evaluation, permissions, budget, run mode, and then automatic bootstrapping…
arbor-agent-executor
Executor-dispatch phase for Arbor. Use when implementing an Idea Tree node through RunExecutor or RunExecutorParallel semantics: isolated git worktree, executor prompt construction, eval metadata injection, RunTraining policy, smoke/full evaluation, report parsing, artifact persistence, tree update, and insight…
arbor-agent-setup-intake
Setup, intake, preflight, and launch-contract phase for open-source Arbor runs. Use when confirming a target project, metric, baseline, dev/test split, config/plugin settings, branch guard, session directory, or when translating a user goal into the precise contract consumed by the coordinator.
arbor-agent-ideate
Strict IDEATE-stage skill for Arbor. Use immediately after TreeView(format="constraints") when drafting Idea Tree nodes, enforcing the ideadrafting and firstprinciplesprobe behavior, depth-aware idea levels, four-line TreeAddNode hypotheses, conflict checks, and self-filtering against shallow tweaks.