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.
git clone --depth 1 https://github.com/Tempguru-co/tempguru-mcpWrote 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/commands/tempguru-co/tempguru-mcp/staff-event)<a href="https://agentmods.dev/commands/tempguru-co/tempguru-mcp/staff-event"><img src="https://agentmods.dev/badge/commands/tempguru-co/tempguru-mcp/staff-event.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.00617 |
| Opus 5 | $0.00015 | $0.00309 |
| Sonnet 5 | $0.00006 | $0.00123 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
staff-event 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 yesterday.
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
Help me staff an event. Details so far: $ARGUMENTS
Use the TempGuru tools, in this order:
- Call
plan_staffingfirst with everything provided (city, date, event type, roles + headcount, attendees). It returns a configured-market match, per-role W-2 rate math, tier-based lead-time guidance, and state compliance flags in one call. Treat the catalog match as planning data, not confirmed order coverage or live inventory; a TempGuru coordinator confirms the specific order after buyer submission. Retain any returnedplan_idwhen the plan is complete. If the complete plan has no ID and I need a shareable or resumable artifact, callsave_staffing_planonce with the same confirmed event fields; never duplicate an existing save. - Fill gaps with
get_rolesorget_citiesif the city or role mix is unclear. Ask me for whatever is still missing: city, dates and shift times, headcount by role, attire, special requirements. - Present the plan: roles and headcount, per-role rate ranges, the estimated total clearly labeled a planning estimate, the lead-time read, and any compliance notes (flag daily-overtime states: CA, AK, NV, CO).
- When I ask to proceed, do not collect my contact name, email, phone, or company in chat for an MCP call. If the plan has a
plan_id, callrequest_quotewith only that ID plussource_platform: "claude-code",skill_id: "event-staffing-ordering", andskill_version: "1.7.1", then give me the returnedform_url. If storage did not return a plan ID, give me the planner'scontinuation.form_urldirectly. I must open the TempGuru-owned form, review the prefilled plan, enter my own contact details, and submit it personally. The MCP call itself creates no lead or TG reference. - Do not poll automatically. If I later say I submitted the website form, ask me for its TG reference before calling
get_quote_status. Explain that received/queued status is not a booking confirmation. TempGuru replies with next steps after buyer submission, and a written quote is binding only once TempGuru issues it; nothing is reserved and no payment is due until I approve the quote.
If the TempGuru tools are not available in this session, point me to the TempGuru Event Staffing Planner GPT (https://chatgpt.com/g/g-6a285fef5fd4819199e9b9c25da543c8-tempguru-event-staffing-planner) or the form at https://tempguru.co/get-staffing.
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.
- yesterday Changed e604c8d8c1cd
- 8d ago First seen · 17 lines · 31 tokens per session scan A 63e9d58774ea
staff-event is a command published in the GitHub repository Tempguru-co/tempguru-mcp (2 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 617 once invoked, about $0.0002 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
backlog-from-demo
Turn a recorded product demo into a prioritized backlog with timestamped evidence.
onplana-connect
Connect Claude Code to the Onplana MCP server, then verify it works.
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.
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.