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.
git clone --depth 1 https://github.com/mikeparcewski/wicked-gardenWrote 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/commands/mikeparcewski/wicked-garden/wg-issue)<a href="https://agentmods.dev/commands/mikeparcewski/wicked-garden/wg-issue"><img src="https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-issue/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/commands/mikeparcewski/wicked-garden/wg-issue"><img src="https://agentmods.dev/badge/commands/mikeparcewski/wicked-garden/wg-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00000 | $0.00436 |
| Opus 5.5 | $0.00000 | $0.00174 |
| Sonnet 5.5 | $0.00000 | $0.00087 |
| Haiku 4.5 | $0.00000 | $0.00044 |
Grade A, and why
wg-issue 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 2mo 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.
What it actually says
/wg-issue
Launch an autonomous ralph-loop to review GitHub issues, batch-resolve them via crew workflow, release, and verify.
Arguments
Parse: $ARGUMENTS
- --list: Just list open issues without starting work (skip ralph-loop)
- --label : Filter issues by label (e.g.,
bug,enhancement) - --limit : Number of issues to show (default: 10)
If --list
List issues only — do NOT start a ralph-loop:
gh issue list --state open --limit "${limit:-10}" ${label:+--label "${label}"} --json number,title,labels,assignees,createdAt,updatedAt
Present issues in a table and stop.
Otherwise: Start Ralph Loop
Invoke the ralph-loop skill with the following prompt:
/ralph-loop:ralph-loop Review our github issues and
- pick a group that makes sense to work on at the same time
- Run a crew to do the work in just finish mode making sure to use council reviews and approvals or to answer questions.
- When the crew is finished, run wg-release.
- Validate the release exists in gh
For any failures use the council for support.
The ralph-loop will autonomously:
- Review open GitHub issues and select a cohesive batch
- Start a crew project in just-finish mode for the batch
- Use council (jam) reviews for approvals and to answer questions
- After crew completion, run
/wg-release(which includes quality gate) - Verify the GitHub release was created successfully
- Use the council for support on any failures
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.
- 2mo ago First seen · 50 lines · 0 tokens per session scan A 786834e39851
wg-issue is a command published in the GitHub repository mikeparcewski/wicked-garden (9 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 436 tokens. 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 2026-08-31.
Other commands, from other repositories
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
sync-github
Ejecuta SonIA Sync: refleja el tablero local en GitHub Issues usando gh CLI.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
test
Test commit. Use for add tests, update tests, test coverage, unit test, spec.
flow
Universal workflow entry point. Use /flow for skill-driven GitHub development. Verbs: start, commit, pr, review, address, merge, resolve, release, status, learn, setup, explain, debug, design, brainstorm, issue.
converge
Run an unattended review→fix→re-review loop on the current branch until the reviewer has no findings at or above Medium, then push once. Findings stay in a local scratch file and are never posted to GitHub. Stops early on oscillation, a red test suite, or a 4-review cap.