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/fmxexpress/pasclaw/hellonpx skills add FMXExpress/PasClaw --skill hellogit clone --depth 1 https://github.com/FMXExpress/PasClawWhat 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 | $0.00012 | $0.00614 |
| Opus 5 | $0.00006 | $0.00307 |
| Sonnet 5 | $0.00002 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
hello 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 2d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hello skill
This is the minimal SKILL.md format PasClaw understands. Drop a directory
named hello/ (the directory name does not need to match name: but it
keeps things readable) under ~/.pasclaw/workspace/skills/ and the
agent will pick it up automatically the next time pasclaw agent,
pasclaw serve, or any other tool-loaded entry point runs.
Frontmatter fields
| Field | Meaning |
|---|---|
name |
Required. The identifier the agent uses to refer to this skill. Lowercase + underscores by convention. |
description |
One-line summary shown in the system prompt's SKILLS section. Keep it short — the model decides whether to consult the SKILL.md based on this line. |
kind |
Optional. shell makes the skill a callable tool that runs the shell: command; prompt returns the rendered prompt: template; omitted (the common case) makes the skill knowledge-only — no tool registered, just markdown the model reads on demand. |
shell |
Required for kind: shell. Shell command line. {{var}} placeholders are substituted from the JSON args before exec. |
prompt |
Required for kind: prompt. Template string returned verbatim with the same {{var}} substitution. |
schema |
Optional JSON schema describing the args object passed to a callable skill. Single-line JSON. Defaults to {"type":"object"} (any args accepted). |
Body conventions (this part)
Everything after the closing --- is markdown. The model loads it via
fs_read when it decides to consult this skill — keep it focused,
well-structured, and treat it as documentation the model will actually
read once and follow. Picoclaw / nanobot / Anthropic agent-skills all
share this format, so a skill written for any of those will work in
PasClaw with no changes (and vice versa).
When to use this skill
Use this skill when the user asks anything containing the word "hello" in the example domain. Since this is the sample skill, the realistic answer is "never in production" — replace this with the trigger conditions that match your actual workflow.
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.
- 2d ago First seen · 52 lines · 12 tokens per session scan A 1e5d1190177a
hello is a skill published in the GitHub repository FMXExpress/PasClaw (53 stars, last pushed 4d ago), licensed MIT. It adds 12 tokens to every session and 614 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.
Other skills, from other repositories
add-telegram-swarm
Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".
penguin-orchestration
Drive PenguinHarness itself from a shell — list and create agents and sessions, send and steer messages mid-flight, and query costs and scheduled tasks via the penguin CLI over the local server.
creating-claude-agents
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.
creating-agent-skills-skill
Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rules.
skill-to-subagent
Turn an existing pi skill into an isolated subagent and wire it into a project's implementation pipeline. Decides fitness first, writes the bridge agent, routes the model, tunes context inheritance, and wires a spawn checkpoint. Use on "wrap this skill as a subagent", "turn X into a subagent", "should this be a…
qodo-pr-resolver
Review and resolve PR issues with Qodo - get AI-powered code review issues and fix them interactively (GitHub, GitLab, Bitbucket, Azure DevOps).