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 stewardgit 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/steward)<a href="https://agentmods.dev/skills/jmagly/aiwg/steward"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/steward/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/steward"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/steward.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 | $0.00023 | $0.03492 |
| Opus 5 | $0.00012 | $0.01746 |
| Sonnet 5 | $0.00005 | $0.00698 |
| Haiku 4.5 | $0.00002 | $0.00349 |
Grade A, and why
steward 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
steward
You provide provider capability awareness and intelligent command routing. You read the canonical capability matrix to answer what the current provider supports natively, what must be emulated, and which command achieves a given goal on the active platform.
Triggers
Alternate expressions and non-obvious activations (primary phrases are matched automatically from the skill description):
- "what can this provider do" → capabilities for current provider
- "is X supported here" → feature check for current provider
- "how do I do X" (in provider context) → routing advice
- "what command handles Y" → find subcommand
- "which model should this use" → model policy route
- "model catalog or routing" →
aiwg steward models - "install or repair AIWG" → public provider-orchestrated setup manifest
- "AIWG setup is stale/broken" → steward repair ladder
- "refresh provider files" → status/doctor, dry-run refresh, then provider redeploy
- "clean up AIWG issues" → discover
issue-audit,aiwg-issue, oraddress-issues
Trigger Patterns Reference
| Pattern | Example | Action |
|---|---|---|
| Current provider capabilities | "what does my provider support" | aiwg steward capabilities |
| Named provider capabilities | "what does Cursor support" | aiwg steward capabilities --provider cursor |
| All providers | "show the full capability matrix" | aiwg steward capabilities --all |
| Feature check | "does my provider support agent teams" | aiwg steward capabilities --feature agent_teams |
| Routing lookup | "which providers support cron" | aiwg steward find --capability cron |
| Model routing | "which model should this use" | aiwg steward models; then aiwg models audit or aiwg models resolve |
| Install or repair AIWG | "get AIWG working in this project" | Follow the public setup.aiwg.yaml; use the self-verifying deployment result, with status and doctor only for audit or recovery |
| Stale provider files | "Codex says skills are missing" | aiwg status --probe --json, aiwg doctor, aiwg refresh --dry-run, then aiwg use all --provider <provider> or aiwg refresh --provider <provider> |
| Stale discovery | "discover cannot find a known skill" | Rebuild and sync the framework index, then re-run discovery |
| Issue cleanup | "clean up stale issues" | Discover first: issue-audit for backlog cleanup, address-issues for implementation, aiwg-issue for AIWG product issues |
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 · 336 lines · 23 tokens per session scan A 94b956187def
steward is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 3,492 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.