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 andreadellacorte/groove --skill groove-work-reviewgit clone --depth 1 https://github.com/andreadellacorte/grooveWrote 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/andreadellacorte/groove/groove-work-review)<a href="https://agentmods.dev/skills/andreadellacorte/groove/groove-work-review"><img src="https://agentmods.dev/badge/skills/andreadellacorte/groove/groove-work-review/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/andreadellacorte/groove/groove-work-review"><img src="https://agentmods.dev/badge/skills/andreadellacorte/groove/groove-work-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00020 | $0.00546 |
| Opus 5 | $0.00010 | $0.00273 |
| Sonnet 5 | $0.00004 | $0.00109 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
groove-work-review 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
groove-work-review
Outcome
The artifact is reviewed for correctness, quality, and fit to plan. Lessons are identified for the compound stage. A clear accept/rework decision is made with rationale. Review notes are captured in the task body.
Acceptance Criteria
- Artifact is evaluated against the plan and acceptance criteria
- Specific gaps or issues are identified (not vague "needs improvement")
- Accept or rework decision is stated with rationale
- Lessons are noted for
/groove-work-compound - Review notes appended to stage task body
- Stage task created in backend:
YYYY-MM-DD, Review
Steps
-
Branch-diff analysis: determine the base branch (default:
main; override withbase:arg if provided). Run:git log --oneline <base>...HEAD— list commits on this branchgit diff <base>...HEAD --stat— summarise changed filesgit diff <base>...HEAD— full diff (use as review input) Use this diff as the primary artifact to evaluate. If no commits beyond base exist, review working-tree changes instead.
-
Evaluate against plan and acceptance criteria — read the plan from the task body or spec file if available.
-
Categorise findings (use these exact labels):
- Fix Now: trivial issues — fix immediately before accepting
- Needs Spec: important gaps requiring planning — create a spec
- Create Issues: large effort or nice-to-have — track as tasks
-
State accept or rework decision with rationale.
-
Note lessons for
/groove-work-compound. -
Append review notes to the task body.
-
Create stage task via
/groove-utilities-task-createiftasks.backend != none(titleYYYY-MM-DD, Review).
Constraints
- Read
tasks.backendfrom.groove/index.mdto determine backend - Be thorough — 80% of compound loop value is here and in plan
- If rework: note specific gaps and link back to which plan step was missed or unclear
- If accept: still note what worked well and what could be improved next time
- Do not skip review even for small changes — capture something
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 · 55 lines · 20 tokens per session scan A 6567dceb1425
groove-work-review is a skill published in the GitHub repository andreadellacorte/groove (5 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 546 once invoked, about $0.0001 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…