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 GuitarAlchemist/ga --skill backlog-groomgit clone --depth 1 https://github.com/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/backlog-groom)<a href="https://agentmods.dev/skills/guitaralchemist/ga/backlog-groom"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/backlog-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/skills/guitaralchemist/ga/backlog-groom"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/backlog-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 | $0.00117 | $0.05058 |
| Opus 5 | $0.00059 | $0.02529 |
| Sonnet 5 | $0.00023 | $0.01012 |
| Haiku 4.5 | $0.00012 | $0.00506 |
Grade A, and why
backlog-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 9d 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 — 482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/backlog-groom
Produces a ranked, justified top-3 next work items for the human to
approve. Pairs with /digest (state cursor) and /grade-last-pr
(post-merge evaluator) to close the planning loop: digest captures the
now, grade-last-pr captures what just shipped, backlog-groom proposes
what next.
This is a Phase 2 harness agent (#3 of 3). Siblings:
semantic-regression-agent (chatbot-qa drift) and token-spend-agent
(AI-cost drift). No file overlap with either.
When to run
- Once per week — Monday morning is the canonical slot. Workflow
.github/workflows/weekly-backlog-grooming.ymlruns every Monday at 8:57 local (off-:00 mark to dodge cron stampedes) and posts the proposal as a comment on the long-lived[meta] Backlog grooming trackerGitHub issue, tagging @spareilleux for go/no-go. - After a major milestone ships — a big PR merge means the cursor moved; the next-3 from before may now be stale.
- At session start when "what should I work on?" is unclear — cheaper than re-deriving priorities from scratch each session.
Do NOT invoke:
- On every session (noise — the prior week's proposal still applies).
- For trivial-scope decisions (a single typo fix doesn't need ranking).
- As a substitute for
/digest(different artifact — state vs proposal).
Why this exists
The current failure mode in autonomous mode is "agent picks whatever's loudest": whichever GitHub issue was opened last, whichever test failure flashed most recently, whichever Slack-message-shaped artifact was most legible. No agent reads the full signal stack (backlog + issues + quality trends + in-flight cursor + stale plans) and emits a justified ranking. This skill is that agent.
Backlog grooming for autonomous work is a one-way door (wrong priorities compound — each wrong week eats a week of opportunity cost), so the skill PROPOSES; the human approves. Even the weekly cron posts a comment, not a dispatch.
Scoring rubric (opinionated, defensible — override at will)
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.
- 9d ago First seen · 482 lines · 117 tokens per session scan A 2956c4791229
backlog-groom is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 5,058 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 skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.