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 steward-quickrefgit 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-quickref)<a href="https://agentmods.dev/skills/jmagly/aiwg/steward-quickref"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/steward-quickref/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-quickref"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/steward-quickref.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 | $0.00057 | $0.01332 |
| Opus 5 | $0.00028 | $0.00666 |
| Sonnet 5 | $0.00011 | $0.00266 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
steward-quickref 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steward Quickref
Thin routing anchor for the three cross-cutting feature domains that no
single framework quickref owns: expansion authoring, persona/SOUL
identity, and project creation. This file holds guidance + anchoring
phrases only — it never inlines skill or agent bodies. The capability index
does the heavy lifting: each row gives the aiwg discover phrase that ranks
the owning capability top-3 (the four discover facets fuse the result —
see src/artifacts/discover-facets.ts).
Always discover, then show. These phrases are the entry points; fetch the selected artifact with
aiwg show <type> <name>. Do not browse the filesystem (skill-discoveryrule).
Steward Tiering
aiwg-steward.md is the Tier-1 dispatch core. This quickref is Tier 2. When
the steward needs detailed lookup tables, route to Tier 3 with
aiwg discover "aiwg-steward routing reference" or
aiwg discover "aiwg-steward worked examples". If a route is ambiguous, ask
one clarifying question; if a target is stale or missing, file a correction
issue through the AIWG issue-filing flow with the broken target and observed
command output.
Domain 1 — Expansion authoring (extension / addon / framework)
"How do I build an AIWG expansion?" — extensions, addons, and frameworks.
| You want to… | Discover phrase | Owning capability |
|---|---|---|
| Author an extension | aiwg discover "author an expansion" |
scaffold-extension |
| Create an addon | aiwg discover "create an addon" |
scaffold-addon |
| Build a framework | aiwg discover "scaffold a framework" |
scaffold-framework |
| Pilot then graduate a project-local bundle | aiwg discover "project-local bundle" |
new-bundle, promote |
| Package a standalone/community plugin repository | aiwg discover "standalone plugin repository" |
package-plugin |
Domain 2 — Persona / SOUL identity (author and select)
"How do I make or choose an identity/voice?" Personas live at
agentic/code/agents/personas/; SOUL profiles are managed by the soul-*
skills.
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 · 116 lines · 57 tokens per session scan A 8bf2fb12efa1
steward-quickref is a skill published in the GitHub repository jmagly/aiwg (211 stars, last pushed 2d ago), licensed MIT. It adds 57 tokens to every session and 1,332 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 2026-09-05.
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.