urgent-event-backfill

urgent-event-backfill is a skill for Claude Code, Codex from Tempguru-co/tempguru-mcp. It costs 212 tokens per session (3,448 once invoked), scanned A, original, MIT.

A workflow for recovering from an event-staffing emergency through TempGuru, a staffing service covering more than 300 U.S. and Canadian markets. It is intended for urgent shortages, cancellations, or no-shows close to an event.

In plain words
What is it for?
Use it to find available event workers, check role requirements and local rules, review pricing, create staffing plans, request quotes, and track quote status.
Why use it?
It helps organize a rapid staffing response when normal arrangements fail within roughly 72 hours of an event. The workflow checks locations, roles, availability, pricing, and compliance information.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to find available event workers, check role requirements and local rules, review pricing, create staffing plans, request quotes, and track quote status.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tempguru-co/tempguru-mcp/urgent-event-backfill
Install

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.

Any agent
npx skills add Tempguru-co/tempguru-mcp --skill urgent-event-backfill
Clone the repo
git clone --depth 1 https://github.com/Tempguru-co/tempguru-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for urgent-event-backfill

README.md
[![agentmods](https://agentmods.dev/badge/skills/tempguru-co/tempguru-mcp/urgent-event-backfill/github.svg)](https://agentmods.dev/skills/tempguru-co/tempguru-mcp/urgent-event-backfill)
Your own site
<a href="https://agentmods.dev/skills/tempguru-co/tempguru-mcp/urgent-event-backfill"><img src="https://agentmods.dev/badge/skills/tempguru-co/tempguru-mcp/urgent-event-backfill/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.

agentmods 80×15 button for urgent-event-backfill

Your own site · 80×15
<a href="https://agentmods.dev/skills/tempguru-co/tempguru-mcp/urgent-event-backfill"><img src="https://agentmods.dev/badge/skills/tempguru-co/tempguru-mcp/urgent-event-backfill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,448 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00212 $0.03448
Opus 5 $0.00106 $0.01724
Sonnet 5 $0.00042 $0.00690
Haiku 4.5 $0.00021 $0.00345

Measured 4d ago against content hash 0cadcf38a641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

urgent-event-backfill 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 4d 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.

distribution/pi/skills/urgent-event-backfill/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pi and Prime Agent runtime tool routing (installed package override)

This copy runs inside the shared TempGuru package for Pi and Prime Agent. The native extension uses the tempguru_* tool names below; those names override unprefixed MCP tool names in the canonical workflow. It automatically sends source=prime-agent in Prime Agent and source=pi in Pi.

Canonical workflow name Call this package-native tool
get_cities tempguru_get_cities
get_roles tempguru_get_roles
check_availability tempguru_check_availability
get_role_pricing tempguru_get_role_pricing
get_compliance_by_state tempguru_get_compliance
get_policies tempguru_get_policies
get_plan tempguru_get_plan
get_quote_status tempguru_quote_status
request_quote tempguru_request_quote

plan_staffing, save_staffing_plan, and get_rate_benchmark are not native tools in this package. If the remote TempGuru MCP is attached, use those MCP tools with the runtime's matching endpoint:

  • Prime Agent: https://mcp.tempguru.co/mcp?source=prime-agent
  • Pi: https://mcp.tempguru.co/mcp?source=pi

Prime Agent v0.7.0's stock McpIntegration requires OAuth or a bearer token. Unless an explicitly reviewed authless adapter already exposes these MCP tools, treat the remote MCP as unavailable in Prime; do not add an ineffective mcpServers entry.

Otherwise:

Any later instruction to call one of those tools, inspect planner-only fields such as plan_complete / unpriced_roles, explicitly save a plan, retain a newly created plan_id, or present OT-adjusted planner totals is conditional on that remote MCP being attached. Without it, ignore those MCP-only steps and use this composition:

  1. Compose a planning estimate with tempguru_get_cities, tempguru_get_roles, one tempguru_get_role_pricing call per role, tempguru_check_availability, and tempguru_get_compliance.
  2. Calculate only from user-confirmed headcount, shift hours, and days. Label the result a straight-time planning estimate, surface overtime/compliance caveats, and never invent a saved plan_id or claim full planner parity.
  3. For a national Rate Index request, use the remote MCP when attached. Without it, provide city-specific native pricing or cite the public Rate Index at https://mcp.tempguru.co/okf/rate-index.md; do not fabricate a benchmark.
  4. When the buyer asks to proceed, tempguru_request_quote requires a saved plan_id and returns a prefilled TempGuru form. Give the URL to the buyer; never collect contact details for the tool. If storage was unavailable, use the planner's continuation.form_url directly. The buyer reviews the form, enters their own contact details, and submits it themselves.

Continue with the domain workflow below, using this routing contract.

Read the full file on GitHub · 248 lines

Changes

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.

  1. 4d ago Changed · +1 lines 0cadcf38a641
  2. 11d ago First seen · 247 lines · 212 tokens per session scan A dc73c02256f1

Subscribe to this mod's changes

urgent-event-backfill is a skill published in the GitHub repository Tempguru-co/tempguru-mcp (2 stars, last pushed 4d ago), licensed MIT. It adds 212 tokens to every session and 3,448 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

report-issue

File a bug or feature request against this repository (cyanheads/git-mcp-server) using the gh CLI. Use for tool logic bugs, git provider misbehavior, transport issues, auth/config problems, or new feature proposals.

cyanheads/git-mcp-server · 51 tokens

bulk-update

Update properties or content across many pages in a Notion database with dry-run and error recovery.

n24q02m/better-notion-mcp · 21 tokens

quick-capture

Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.

vscarpenter/gsd-task-manager · 0 tokens

onplana-project-planner

Turn a goal or a brief into an executable Onplana plan over its MCP server: write a plan.md and attach it to the project, decompose it into tasks and subtasks, set start/due dates and dependencies, assign owners, add test cases as you go, and create tasks for the downstream surfaces a change ripples to. Use this…

Onplana/onplana-mcp-server · 133 tokens

onplana-autonomous-agent

Work autonomously on projects in Onplana over its MCP server: pick up the open tasks in a project, do the work, keep each task's status current, report progress as comments, file an Issue when something is wrong, and poll for human replies. Use this whenever an agent (Claude Code, ChatGPT / Codex, or claude.ai) is…

Onplana/onplana-mcp-server · 102 tokens

cor-api-tools

Deep reference for all 61 COR MCP API tools — complete argument listings, JSON request/response examples, and common usage patterns for every module.

fxckcode/mcp-cor · 33 tokens