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-prep-deliverygit 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-prep-delivery)<a href="https://agentmods.dev/skills/jmagly/aiwg/steward-prep-delivery"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/steward-prep-delivery/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-prep-delivery"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/steward-prep-delivery.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 | $0.00032 | $0.01337 |
| Opus 5 | $0.00016 | $0.00668 |
| Sonnet 5 | $0.00006 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
steward-prep-delivery 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 5d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Steward Prep for Delivery (#1269)
You are walking the user through filing a high-quality issue or PR, mirroring the import pattern used for the recent jmagly→roctinam tester report sweep (Gitea #1264–#1269).
When this fires
- "I want to file an issue"
- "I want to open a PR"
- "Help me file a bug report"
- "Should this be a new issue or a comment on an existing one?"
- "Walk me through the import flow for this tester report"
The walkthrough
Step 1: Triage
Ask the user: "Is this one bug, or did you find multiple issues in a single session?"
- One issue → use
bug-report.md(orfeature-request.mdif it's a proposal, not a defect) - Multiple findings → use
tester-report.mdand split during triage - Already filed elsewhere (GitHub, Discord, email) → use
imported-report.md
Don't make this decision for them — surface the templates and let them pick.
Step 2: Environment capture (for bug reports)
For bug-report.md, the operator needs to fill in environment info. Help them collect it:
aiwg version
aiwg doctor
node --version
uname -a # OS / kernel
If they're filing on behalf of an agent platform (Claude Code, hermes, Codex, …), make sure the platform name is captured — the same bug can manifest differently across providers.
Step 3: Duplicate detection (BEFORE filing)
Run the duplicate-detection helper. The skill's script: entrypoint
(find-duplicates.sh) searches the local aiwg discover index plus the Gitea
issue tracker for likely duplicates of the proposed title or keywords:
aiwg run skill steward-prep-delivery -- "<keywords from the issue title>"
Output: ranked list of existing open issues that match. If any look like duplicates, prefer commenting on them over filing a new one. If none match, proceed to filing.
Step 4: Draft assembly
Help the user fill out the chosen template. Specifically:
- For bug-report.md: insist on a copy-paste-able repro (not "X seems broken"). Paste exact error text in code blocks.
- For feature-request.md: insist on a concrete proposal (interfaces, file paths, command syntax) — not "we should make X better."
- For tester-report.md: encourage one finding per section with severity, repro, expected/actual.
- For imported-report.md: include the source link, original reporter handle, and platform/environment correction if the source got it wrong (e.g., the jmagly tester report cited Claude Code, but the actual harness was hermes).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 120 lines · 32 tokens per session scan A 2111c56e5fb9
steward-prep-delivery is a skill published in the GitHub repository jmagly/aiwg (210 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,337 once invoked, about $0.0002 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
cross-repo-cache
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…
implement-issue
Drive a GitHub issue from branch to pull request — read the issue, create a feature branch, implement the change, run the project's build and tests, then commit, push, and open a PR. Language and build-tool agnostic. Use when asked to implement, fix, or resolve a GitHub issue by number.
fest-execution
Execute active festival tasks. Use when finding the next task, marking tasks completed/blocked/reset, committing with festival traceability, advancing workflow steps, and validating sequence progress.
camp-projects
Manage a camp's projects. Use when committing inside projects/, deciding status/pull/push scope (root vs submodule vs all), or creating/removing project worktrees.
flo
MoFlo ticket spell - analyze and execute GitHub issues.
reset-epic
Reset an epic's test data — close PRs, delete branches, reopen issues, revert code.