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 agentmods add commands/raghatatepiyush/ringmaster/pickupgit clone --depth 1 https://github.com/raghatatepiyush/ringmasterWhat 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 | $0.00026 | $0.00359 |
| Opus 5 | $0.00013 | $0.00179 |
| Sonnet 5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
pickup 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 2d 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.
What it actually says
You are resuming a Ringmaster session. Follow the pickup / resume flow in
${CLAUDE_PLUGIN_ROOT}/skills/orchestrator/references/state-and-resume.md exactly:
- Read
.ringmaster/state.jsonand.ringmaster/PROGRESS.md. If neither exists, say so plainly and offer to start fresh — do not invent a ledger. - Validate:
python "${CLAUDE_PLUGIN_ROOT}/hooks/ledger.py" validate .ringmaster/state.json(usepython3orpyifpythonisn't on PATH). If it reports problems, surface them and ask before proceeding. - Reconcile (trust but verify): run read-only
git status/git diff --stat, confirm the recordedfilesTouchedstill exist, and detect drift (files moved, tasks completed elsewhere, new commits). If anything is ambiguous, flag it and ask before resuming; update the ledger to match reality. - Print a compact resume briefing (goal; done / in-progress / pending / blocked
counts; key decisions; the next task) using the block in
${CLAUDE_PLUGIN_ROOT}/skills/orchestrator/references/output-style.md. - Select the next task (
python "${CLAUDE_PLUGIN_ROOT}/hooks/ledger.py" next .ringmaster/state.json, or the documented algorithm) and continue it through the normal orchestrator pipeline — behind the stage-1 approval gate if it is substantial.
Honor every safety rail. Stage, never commit.
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.
- 2d ago First seen · 25 lines · 26 tokens per session scan A e22fef4900ed
pickup is a command published in the GitHub repository raghatatepiyush/ringmaster (1 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 359 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.