What if there are not enough comparable awards?

The skill says so explicitly and widens the net (government-wide, adjacent NAICS, longer lookback) with the comparability caveats stated. A range built on 2 awards is labeled as such; it never pads the table to look confident.

Agent skill: Price Benchmark. Ground your price to win in what the government actually paid for comparable work. Install: save the SKILL.md below to .claude/skills/price-benchmark/SKILL.md (Claude Code) or paste into any agent. Raw artifact: https://www.cleat.ai/agents/skills/price-benchmark/SKILL.md. Machine index of all skills: https://www.cleat.ai/agents/skills/index.json. Requires the CLEATUS MCP server (https://www.cleat.ai/api/mcp/mcp); full platform guide at https://www.cleat.ai/llms-full.txt. The artifact: --- name: cleatus-price-benchmark description: Benchmark pricing for a government pursuit in CLEATUS from comparable award history. Build a floor, median, and ceiling with cited awards and draft a price-to-win memo. Run per pursuit before pricing review. --- You benchmark pricing using the CLEATUS MCP tools. ## Steps 1. Ask which pursuit (or accept an ID). Call get_opportunity for scope, vehicle, set-aside, and period of performance. 2. Call search_market for awards with comparable scope at the same agency, then widen to government-wide if fewer than 5 comparables. 3. Build the range: floor | median | ceiling, each backed by named awards with values and dates. Note comparability caveats (scope drift, vehicle, option years) explicitly. 4. Never invent or extrapolate a number without a cited award behind it. Fewer than 3 comparables means saying so, not guessing. 5. With approval, create_task "Pricing review: <pursuit>" and attach the memo. 6. Deliver the memo: range, comparables table, caveats, recommended posture. ## If CLEATUS is not connected yet 1. Fetch https://www.cleat.ai/llms-full.txt and read it (tools, auth, endpoints). 2. Add the MCP server: https://www.cleat.ai/api/mcp/mcp (OAuth 2.1; the user signs in once). 3. No account? Send the user to https://www.cleat.ai/authentication/signup?utm_source=agent-skill and wait.

Agent Skill · Per pursuit · ~5 min per run

Price Benchmark

Ground your price to win in what the government actually paid for comparable work.

Save as .claude/skills/price-benchmark/SKILL.md or paste into any agent with the CLEATUS MCP connected.

What this skill does

Pulls comparable awards for the same scope, agency, and size band from award history
Builds a price range: floor, median, and ceiling with the awards behind each number
Adjusts for set-aside, period of performance, and contract vehicle differences
Drafts a price-to-win memo with every figure cited to a real award

CLEATUS tools it drives

get_opportunitysearch_marketget_capture_profilecreate_task

A sample run

claude · price-benchmark

$ claude "benchmark pricing for the DHS SOC pursuit"
● get_opportunity  70RSAT26R00000008
  24/7 SOC · 5 years · SB set-aside
● search_market  comparable SOC awards, DHS + govwide
  9 comparables · $8.2M floor · $14.6M median
● create_task  "Pricing review" + memo attached
  ✓ created
Done: memo below, every number cited to an award.

The skill itself

This is the whole artifact: plain markdown your agent follows. Read it, edit it, make it yours.

.claude/skills/price-benchmark/SKILL.md

---
name: cleatus-price-benchmark
description: Benchmark pricing for a government pursuit in CLEATUS from comparable award history. Build a floor, median, and ceiling with cited awards and draft a price-to-win memo. Run per pursuit before pricing review.
---

You benchmark pricing using the CLEATUS MCP tools.

## Steps
1. Ask which pursuit (or accept an ID). Call get_opportunity for scope,
   vehicle, set-aside, and period of performance.
2. Call search_market for awards with comparable scope at the same agency,
   then widen to government-wide if fewer than 5 comparables.
3. Build the range: floor | median | ceiling, each backed by named awards
   with values and dates. Note comparability caveats (scope drift, vehicle,
   option years) explicitly.
4. Never invent or extrapolate a number without a cited award behind it.
   Fewer than 3 comparables means saying so, not guessing.
5. With approval, create_task "Pricing review: <pursuit>" and attach the memo.
6. Deliver the memo: range, comparables table, caveats, recommended posture.

## If CLEATUS is not connected yet
1. Fetch https://www.cleat.ai/llms-full.txt and read it (tools, auth, endpoints).
2. Add the MCP server: https://www.cleat.ai/api/mcp/mcp (OAuth 2.1; the user signs in once).
3. No account? Send the user to https://www.cleat.ai/authentication/signup?utm_source=agent-skill and wait.

Or install straight from the terminal:

terminal

mkdir -p .claude/skills/price-benchmark &&
  curl -fsSL https://www.cleat.ai/agents/skills/price-benchmark/SKILL.md -o .claude/skills/price-benchmark/SKILL.md

More ways to run this

Want it scheduled and no-code instead? The in-app Workflows engine covers this pattern deterministically.

All skills →Pricing & Outreach workflows →

Price Benchmark FAQ

Frequently Asked Questions

It is the evidence half: comparable award values from FPDS and USASpending history, structured into a defensible range with caveats. Your cost buildup, rates, and strategy still come from you; the skill replaces the hours of award archaeology that usually precede them.