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 setup-rungit 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/setup-run)<a href="https://agentmods.dev/skills/jmagly/aiwg/setup-run"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/setup-run/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/setup-run"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/setup-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 221 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 76 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Agent Snooping · line 242 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00021 | $0.01999 |
| Opus 5.5 | $0.00008 | $0.00800 |
| Sonnet 5.5 | $0.00004 | $0.00400 |
| Haiku 4.5 | $0.00002 | $0.00200 |
Grade A, and why
setup-run 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 1mo 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
setup-run
Execute a setup.aiwg.io/v1 SetupManifest, performing cross-platform installation step by step.
This skill executes deterministic manifests. If
metadata.execution_mode: provider-orchestrated, validate the manifest and
hand it to the current supported AI provider; do not begin deterministic CLI
execution.
Trigger Phrases
- "run the setup manifest"
- "install using setup.manifest.yaml"
- "execute installer for [project]"
- "aiwg setup-run [manifest]"
- "run setup for [project]"
- "run dev setup for [project]"
Parameters
manifest (positional, optional)
Path to the setup.manifest.yaml. Default: ./setup.manifest.yaml.
--dry-run (optional)
Print what would be executed without running any scripts.
--platform (optional)
Override platform detection: linux, macos, windows, wsl2.
--distro (optional)
Override distro detection: ubuntu, debian, fedora, arch, etc.
--params-file (optional)
Path to a YAML file with pre-set param values (avoids interactive prompts).
--step (optional)
Run only a specific step by id. Useful for resuming after failure.
--skip (optional)
Comma-separated step IDs to skip.
--type (optional)
Filter which manifest to run by install type: user, developer, or ci.
When --type developer is specified and no manifest path is given, the skill looks for installer/setup.dev.manifest.yaml before falling back to setup.manifest.yaml.
When --type user is specified, the skill looks for installer/setup.user.manifest.yaml.
Execution Flow
Phase 1: Load and Validate
- Read the manifest file
- Validate against
setup.aiwg.io/v1schema (run setup-validate internally) - If invalid, report errors and stop — do not attempt partial execution
Phase 2: Platform Detection
- Detect OS:
uname -s(Linux/Darwin) or$PSVersionTable(Windows) - Detect distro:
/etc/os-release→IDfield - Detect arch:
uname -m - Detect shell:
$SHELLor$0 - Match against manifest
platformblock — if no match, warn and ask to proceed or abort
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.
- 1mo ago First seen · 243 lines · 21 tokens per session scan A 4b52100bf507
setup-run is a skill published in the GitHub repository jmagly/aiwg (224 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,999 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 2026-08-30.
Other skills, from other repositories
builder
Implementing robust business logic, API integrations, data models, and reproducible AI image-generation code with type safety. Use for production implementation, Gemini image API pipelines, or interactive pair programming.
matrix
Controlling combinatorial explosion across multi-dimensional axes: minimum coverage sets, execution plans, test/deploy/UX/risk prioritization. Use when scoping multi-axis combinations.
nexus
Orchestrating multi-specialist task chains and scope-adaptive product delivery: classifies intent, selects and executes the minimum viable chain, aggregates results, and verifies acceptance criteria. For multi-domain tasks, build-first delivery, and product lifecycle execution.
oracle
Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.
scribe
Authoring standalone and cross-team specifications: PRD/SRS/HLD/LLD, staged L0-L4 unified packages, BDD acceptance criteria, and traceability. Use for technical or multi-audience documentation; not implementation or architecture decisions.
tome
Converting technical knowledge into durable learning documents and publishable articles. Use for diff-based teaching, decision records, onboarding, note/Zenn/Qiita/dev.to posts, article series, retrospectives, and cross-platform repurposing.