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/skyfox675/agents-skillsWrote 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/skyfox675/agents-skills/gh-issue-groom)<a href="https://agentmods.dev/commands/skyfox675/agents-skills/gh-issue-groom"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/gh-issue-groom/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/skyfox675/agents-skills/gh-issue-groom"><img src="https://agentmods.dev/badge/commands/skyfox675/agents-skills/gh-issue-groom.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 | $0.00114 | $0.01047 |
| Opus 5 | $0.00057 | $0.00524 |
| Sonnet 5 | $0.00023 | $0.00209 |
| Haiku 4.5 | $0.00011 | $0.00105 |
Grade A, and why
gh-issue-groom 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 11d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gh-issue-groom — groom a story to ≥90% intent before tech review
Operate in caveman mode (load the
cavemanskill) for working output. Keepghcommands, labels, theGROOMcontract line, and any existing acceptance-criteria text byte-exact; the body prose you write is the exception (humanizer — see the grooming-issues skill).
Arguments: $ARGUMENTS
Parse them as:
- One or more issue numbers (with or without
#). Each is a raw, vague, or half-written issue that is not yet ready for development. A lead may drop several at once. - Optional
model:<tier>/effort:<level>, anywhere — these pin the grooming agent's tier (defaultsonnet).
Example: /gh-issue-groom 530 531
The grooming-issues skill is the protocol — the ≥90%-intent bar, the question channels, what may and may not be written to the body, the verdict states, and the output contract all come from it. Grooming captures the what and why; the how and the LoE come later from /gh-issue-recon. Consult the skill before starting.
Hard rule (from grooming-issues): do not modify acceptance criteria already written in the issue unless the operator explicitly asks in this run. Existing AC is an approved contract. If it looks wrong, raise it as a question — don't rewrite it.
Steps
-
Resolve the batch. Collect the issue numbers (strip
model:/effort:first). For each,gh issue view <N> --json title,body,labels,state; skip and report any closed or holdingdo-not-dispatch. -
Fan out, one grooming agent per issue, in parallel (single message, per the dispatching-subagents skill). Each agent is briefed with the grooming-issues sandbox verbatim, including the AC-preservation hard rule. It first reads any prior grooming questions + answers on the issue (a rerun resumes, not restarts), reads the issue and its linked context (only light repo reading for context — deep tracing is recon's job), and writes no code, asserts no LoE/technical approach, and never claims the issue.
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.
- 11d ago First seen · 37 lines · 114 tokens per session scan A 815916c58a22
gh-issue-groom is a command published in the GitHub repository skyfox675/agents-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 114 tokens to every session and 1,047 once invoked, about $0.0006 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 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.