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 1102tools-dev/federal-contracting-skills --skill igce-builder-lh-tmgit clone --depth 1 https://github.com/1102tools-dev/federal-contracting-skillsWrote 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/1102tools-dev/federal-contracting-skills/igce-builder-lh-tm)<a href="https://agentmods.dev/skills/1102tools-dev/federal-contracting-skills/igce-builder-lh-tm"><img src="https://agentmods.dev/badge/skills/1102tools-dev/federal-contracting-skills/igce-builder-lh-tm/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/1102tools-dev/federal-contracting-skills/igce-builder-lh-tm"><img src="https://agentmods.dev/badge/skills/1102tools-dev/federal-contracting-skills/igce-builder-lh-tm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00147 | $0.04221 |
| Opus 5 | $0.00073 | $0.02110 |
| Sonnet 5 | $0.00029 | $0.00844 |
| Haiku 4.5 | $0.00015 | $0.00422 |
Grade A, and why
igce-builder-lh-tm 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 12d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IGCE Builder: Labor-Hour and Time-and-Materials
Overview
Product quality default
Build a route-specific operational estimate. The summary begins with the requirement, whether the estimate is LH or T&M, the decision supported, ceiling or labor basis, material assumptions, top drivers, limitations, and next human action. Use Labor-Hour Independent Government Cost Estimate — [Requirement] or Time-and-Materials Independent Government Cost Estimate — [Requirement], never a generic evidence-brief title. Keep rate evidence and source inputs in their own sheets; keep materials separate from labor and do not convert neutral benchmarking into a procurement conclusion.
Build an auditable Labor-Hour or Time-and-Materials Independent Government Cost Estimate. Both contract types use fixed hourly rates that include wages, overhead, G&A, and profit. T&M also reimburses materials at actual cost, subject to the contract and applicable indirect-cost treatment; LH does not include a materials-reimbursement component.
Regulatory anchors: FAR 15.404-1, FAR 16.600 and 16.601, FAR 31.205-26, and FAR 52.232-7. Apply the current regulation, solicitation, clauses, and agency supplement. This skill does not prepare the Determination and Findings required to use T&M/LH or make legal determinations.
Load supporting files only when needed:
- wrap-rate-presets.md for burden-multiplier scenarios.
- data-source-operations.md before mapping labor or calling BLS, CALC+, or Per Diem.
- workbook-specification.md before creating a workbook.
- professional-product-standard.md before creating a workbook.
- validation-gates.md before and after workbook generation.
- runtime-adaptation.md for questions, tools, formula engines, and delivery.
Operating principle
What ships with it
11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 297 B
- references/data-source-operations.md 13 KB
- references/professional-product-standard.md 5.5 KB
- references/runtime-adaptation.md 2.7 KB
- references/validation-gates.md 4.7 KB
- references/workbook-specification.md 12 KB
- references/wrap-rate-presets.md 2.8 KB
- scripts/recompute_expected_values.py 8.8 KB runs code
- scripts/validate_workbook.py 43 KB runs code
- test.md 3.8 KB
- testing.md 32 KB
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.
- 12d ago First seen · 253 lines · 147 tokens per session scan A e00c5a4d7ffb
igce-builder-lh-tm is a skill published in the GitHub repository 1102tools-dev/federal-contracting-skills (25 stars, last pushed 12d ago), licensed MIT. It adds 147 tokens to every session and 4,221 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
estimating-price-to-win
Produces a price-to-win analysis for a US Federal opportunity. Use when the user needs price-to-win, PTW, a competitive pricing analysis, a price target or price range, or wants to understand pricing strategy, cost drivers, and pricing levers for a federal bid. Estimates the competitive price range and a target price…
narrating-cost-volumes
Drafts the cost or price volume narrative and basis-of-estimate text for a US Federal proposal. Use when the user needs a cost volume narrative, price volume narrative, cost narrative, basis of estimate or BOE, cost-realism narrative, or to check cost-technical consistency for a federal bid. Explains and justifies…
helius-jupiter
Skill "helius-jupiter" from helius-labs/core-ai, covering helius x jupiter — build defi apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. jupiter api key.
helius-okx
Skill "helius-okx" from helius-labs/core-ai, covering helius x okx — build trading & intelligence apps on solana, mcp router surface, prerequisites, 1. helius mcp server and 2. okx skill library (required).
auditing-commitments
Audits a US Federal proposal draft for the obligations it creates, and flags promises stronger than the solicitation requires. Use when the user needs a commitment audit, a promise review, an obligation review, a check for overcommitting, a review of "we will" and "shall" language, a check that the draft does not…
reviewing-color-teams
Runs proposal color team reviews for a US Federal bid — Blue, Pink, Green, Red, Gold, and White Glove. Use when the user needs a color team review; a Blue, Pink, Green, Red, Gold, or White Glove (book check) review; a proposal or cost-volume review; an evaluator-perspective assessment; a mock evaluation; or a proposal…