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-admin-installgit 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-admin-install)<a href="https://agentmods.dev/skills/andreadellacorte/groove/groove-admin-install"><img src="https://agentmods.dev/badge/skills/andreadellacorte/groove/groove-admin-install/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-admin-install"><img src="https://agentmods.dev/badge/skills/andreadellacorte/groove/groove-admin-install.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket warn
- Snyk warn
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 | $0.00023 | $0.01558 |
| Opus 5 | $0.00012 | $0.00779 |
| Sonnet 5 | $0.00005 | $0.00312 |
| Haiku 4.5 | $0.00002 | $0.00156 |
Grade A, and why
groove-admin-install 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
groove-admin-install
Outcome
All groove backends are installed in dependency order, companion skills and groove skill symlinks are present (first install is not complete without them), AGENTS.md contains the session bootstrap, and the repo is ready for use.
Acceptance Criteria
- Task and memory backends installed (or clearly reported if a step failed)
- Companion skills installed (find-skills, agent-browser, pdf-to-markdown) — required; verify each
SKILL.mdexists after step 4 - Platform symlinks —
.claude/skills/groove*and.cursor/skills/groove*point at.agents/skills/groove*— required on every install run - User sees a summary of what was installed, including ✓/✗ for companions and symlinks
Steps
Run in order:
- If
.groove/index.mddoes not exist, run/groove-admin-config --defaultsto create it with all defaults (no prompts) - Run
/groove-utilities-task-install— installs the configured task backend (e.g. beans) - Run
/groove-utilities-memory-install— creates memory directories - Install companion skills (mandatory — do not skip): On first install and every later run, ensure these exist under
.agents/skills/. IfSKILL.mdis missing, run the matchingnpx skills addcommand; on transient failure, retry once, then report failure (install is not complete until all three succeed).- find-skills (downloaded):
test -f .agents/skills/find-skills/SKILL.mdornpx skills add https://github.com/vercel-labs/skills --skill find-skills - agent-browser (downloaded):
test -f .agents/skills/agent-browser/SKILL.mdornpx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser - pdf-to-markdown (embedded):
test -f .agents/skills/pdf-to-markdown/SKILL.mdornpx skills add andreadellacorte/groove --skill pdf-to-markdown - Afterward, verify:
test -feach of the threeSKILL.mdpaths — if any missing, stop and report install incomplete (do not claim success). - Report each as installed / already-present / failed
- find-skills (downloaded):
- Sync platform skill directories via symlinks (mandatory — do not skip): Groove skills must be linked into each editor’s skills tree so
groove-*commands resolve.- Create parent dirs if missing:
mkdir -p .claude/skills .cursor/skills(Claude Code expects.claude/skills/; Cursor expects.cursor/skills/) - For each directory in
.agents/skills/that starts withgroove:- Create
.claude/skills/<name>as a symlink →../../.agents/skills/<name> - Create
.cursor/skills/<name>as a symlink →../../.agents/skills/<name>
- Create
- Run:
mkdir -p .claude/skills .cursor/skills && for skill in .agents/skills/groove*; do name=$(basename "$skill"); ln -sfn "../../.agents/skills/$name" ".claude/skills/$name"; ln -sfn "../../.agents/skills/$name" ".cursor/skills/$name"; done - Note: use
ln -sfn(no-dereference) —ln -sfon an existing directory symlink follows the symlink and creates a nested symlink inside the target directory - Verify: at least one
groove-*name exists under.agents/skills/and matching symlinks exist under.claude/skills/and.cursor/skills/ - Report: "✓ platform symlinks updated (.claude/skills/, .cursor/skills/)" or report failure
- Create parent dirs if missing:
- Scaffold hooks and cache directories:
- Create
.groove/hooks/if it does not exist - Create
.groove/.cache/if it does not exist (with a.gitkeep) - If
.groove/hooks/start.mddoes not exist, create it with:# Hook: Session Start Runs automatically at the end of `/groove-daily-start`. Add items to `## Actions` to automate session-start tasks. ## Actions <!-- Add actions here, one per line. Examples: - Run `git fetch --all` to refresh remote refs - Print "Good morning — groove is ready" --> - If
.groove/hooks/end.mddoes not exist, create it with:# Hook: Session End Runs automatically at the end of `/groove-daily-end`. Add items to `## Actions` to automate session-end tasks. ## Actions <!-- Add actions here, one per line. Examples: - Run `git push` to push today's commits - Print "Session closed — see you tomorrow" --> - Report hooks: created / already-present
- Create
- Apply git strategy — write
.groove/.gitignorefromgit.*sub-keys in.groove/index.md(see/groove-admin-configfor rules)
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 · 101 lines · 23 tokens per session scan A 412695620f3b
groove-admin-install is a skill published in the GitHub repository andreadellacorte/groove (5 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 1,558 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.