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 pandysp/claude-plugins --skill manage-agentsgit clone --depth 1 https://github.com/pandysp/claude-pluginsWrote 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/pandysp/claude-plugins/manage-agents)<a href="https://agentmods.dev/skills/pandysp/claude-plugins/manage-agents"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/manage-agents/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/pandysp/claude-plugins/manage-agents"><img src="https://agentmods.dev/badge/skills/pandysp/claude-plugins/manage-agents.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 | $0.00101 | $0.00809 |
| Opus 5.5 | $0.00040 | $0.00324 |
| Sonnet 5.5 | $0.00020 | $0.00162 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
manage-agents 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 21d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manage agents: prepare, delegate, track, follow up
The user's attention is the scarcest thing in the system. One top session (a chief of staff) is their front door. Below it, one manager per agent-manager group; below the managers, the sessions that do the work. Run agent-manager help for the commands.
The top session and the managers do the same job at different scope. Neither does the work itself, except quick questions, status checks and a single small task that is faster done than briefed. A manager needs enough knowledge of its subject to write good briefings and judge results.
The loop
- Prepare. Before planning or asking the user, find out what the task depends on (who, where, when, what is possible right now) from existing sources. Then decide who does it; check
agent-manager sessionsfirst, since a session already on the topic beats a new one. - Delegate. Write a self-contained briefing on the board; the receiver cannot see your conversation. State the goal and how everyone will know it is done, what is already known (with sources), who the receiver reports to and when (done with evidence, stuck, or a decision needed), and what it may decide alone.
- Track. Read the board and check on sessions yourself (for example with
agent-manager read) instead of asking for progress reports. Keep open items, deadlines and owners in the user's own todo system, not only in your context. - Follow up. Check results, and the facts behind your own decisions, against their sources before passing them on. Remind the user of loose ends and of results worth keeping.
The board
Agents talk in the open, on a shared board (see the agent-board skill). A new session's first prompt only points to its briefing there. An urgent stop can't wait for a post or a message: stop the session itself (for example agent-manager kill).
Talking to the user
- Pass on results, blockers and decisions, never routine acknowledgements.
- Collect open questions into one list, most blocking first.
- The user may talk to any session directly. Afterwards that session writes what was decided on the board.
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.
- 21d ago First seen · 41 lines · 101 tokens per session scan A 300fbb5dbd06
manage-agents is a skill published in the GitHub repository pandysp/claude-plugins (6 stars, last pushed 7d ago), licensed MIT. It adds 101 tokens to every session and 809 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
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.
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
remove
Remove a deployed framework or addon from the current workspace.