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 jmagly/aiwg --skill skillsgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/skills)<a href="https://agentmods.dev/skills/jmagly/aiwg/skills"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/skills/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/jmagly/aiwg/skills"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.01093 |
| Opus 5 | $0.00010 | $0.00547 |
| Sonnet 5 | $0.00004 | $0.00219 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
skills 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 7d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Registry
You manage the AIWG skills registry — listing installed skills, searching the registry, fetching skill details, installing skills, and publishing skills to ClaWHub/OpenClaw.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "what skills do I have" → list
- "find a skill for git" → search git
- "how does the deploy-gen skill work" → info deploy-gen
- "get the roko-voice skill" → install roko-voice
- "share this skill" → publish
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| List installed | "what skills are installed?" | Run aiwg skills list |
| Search registry | "search for skills related to voice" | Run aiwg skills search voice |
| Skill details | "tell me about the mention-wire skill" | Run aiwg skills info mention-wire |
| Install skill | "install the commit-and-push skill" | Run aiwg skills install commit-and-push |
| Publish skill | "publish this skill to the registry" | Run aiwg skills publish <path> |
Behavior
When triggered:
-
Identify the subcommand:
- Is the user listing, searching, inspecting, installing, or publishing?
- Is a skill ID or search query mentioned?
-
Run the appropriate command:
# List locally installed skills aiwg skills list # Search the registry aiwg skills search <query> # Show details for a specific skill aiwg skills info <skill-id> # Install a skill from the registry aiwg skills install <skill-id> # Publish a skill to the registry aiwg skills publish <skill-path> # Machine-readable output aiwg skills list --json aiwg skills search <query> --json -
Report the result — confirm what was found, installed, or published.
Examples
Example 1: List installed skills
User: "What skills are installed?"
Extraction: List subcommand
Action:
aiwg skills list
Response: "47 skills installed. Categories: devkit (8), workspace (5), voice (6), mention (5), soul (7), deploy (4), other (12). Run aiwg skills info <id> for details."
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.
- 7d ago First seen · 145 lines · 20 tokens per session scan A dcc302671775
skills is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,093 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 2026-09-05.
Other skills, from other repositories
surge
Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…
horizon
Run a durable Horizon workflow for a multi-feature goal with bounded autonomous retries and an audit trail.
check-in
Record a Parallax protocol checkpoint with concrete evidence before gated implementation work.
debug
Perform an evidence-based Parallax diagnosis or post-build audit and verify the repair.
hyperplan
Harden a non-trivial plan through a three-round adversarial critique and evidence-based synthesis.