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 danielkinneyspears/federal-proposal-skills --skill writing-past-performancegit clone --depth 1 https://github.com/danielkinneyspears/federal-proposal-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/danielkinneyspears/federal-proposal-skills/writing-past-performance)<a href="https://agentmods.dev/skills/danielkinneyspears/federal-proposal-skills/writing-past-performance"><img src="https://agentmods.dev/badge/skills/danielkinneyspears/federal-proposal-skills/writing-past-performance/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/danielkinneyspears/federal-proposal-skills/writing-past-performance"><img src="https://agentmods.dev/badge/skills/danielkinneyspears/federal-proposal-skills/writing-past-performance.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.01546 |
| Opus 5 | $0.00044 | $0.00773 |
| Sonnet 5 | $0.00018 | $0.00309 |
| Haiku 4.5 | $0.00009 | $0.00155 |
Grade A, and why
writing-past-performance 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 11d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Past Performance
Build the past performance write-ups: the evidence that the offeror has done work like this before and done it well. Federal evaluators assess past performance for three things (recency, relevancy, and quality) and they assess relevancy strictly, against the current requirement. A past performance volume that lists impressive contracts without proving they resemble this work earns far less than the contracts deserve. This skill writes to the three tests.
When to use this skill
Use this skill to develop the past performance volume or past performance citations for a federal proposal. It works from a library of the offeror's (and teaming partners') prior contracts.
It does not write key-personnel experience — that is developing-key-personnel.
Past performance is about organizational performance on prior contracts.
Inputs
Required:
- The solicitation's past performance instructions (Section L) and evaluation criteria (Section M) — they define recency, relevancy, the reference count and format, and how quality is judged.
- A past performance library in
source/— the prior contracts available to cite, with their facts (customer, value, period, scope) and any performance records (CPARS ratings, PPQs, award fees, metrics).
Preferred upstream artifacts:
10-compliance-matrix.md: the past performance requirement rows.05-win-strategy.md: past performance is often a major proof source for win themes; coordinate.
Without performance records, the write-ups can still describe relevance, but flag every unsubstantiated quality claim — quality with no evidence is weak.
Read ../../shared/glossary.md, ../../shared/federal-solicitation-primer.md,
and ../../shared/pursuit-workspace.md if not already read this session.
Intake
Ask these as a numbered list. Skip what the solicitation answers.
- The rules. What does Section L require — how many references, what format, what page or word limit each, prime vs. subcontractor references, the recency window (how far back counts)?
- The relevancy definition. How does Section M define relevancy — on scope, size/dollar value, complexity, contract type, customer, place of performance? What does it count as "similar"?
- The library. What prior contracts are available to cite, and for each: customer, value, period of performance, scope, the offeror's role (prime/sub), and any performance evidence?
- Quality evidence. What performance records exist — CPARS ratings, PPQs, award-fee history, customer commendations, quantified outcomes?
- Known problems. Did any candidate reference have performance problems? If so, what happened and what was the corrective action?
What ships with it
2 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.
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.
- 11d ago First seen · 139 lines · 89 tokens per session scan A ca29086c1a89
writing-past-performance is a skill published in the GitHub repository danielkinneyspears/federal-proposal-skills (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 1,546 once invoked, about $0.0004 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 skills, from other repositories
analyzing-competitors
Produces a Black Hat competitive assessment for a US Federal opportunity as a wiki of competitor entities. Use when the user needs competitive analysis, a Black Hat review or session, competitor profiling, an incumbent assessment, or to understand the competitive field for a federal bid. Creates and enriches one…
qualifying-opportunities
Runs a structured bid/no-bid gate review for a US Federal opportunity and bootstraps the pursuit's knowledge wiki. Use when deciding whether to pursue or bid a federal solicitation, RFP, RFQ, RFI, sources-sought notice, or IDIQ task order — for a bid/no-bid decision, pursuit decision, gate review, opportunity…
igce-builder-ffp
Trigger for: FFP IGCE, firm-fixed-price estimate, FFP cost model, proposed FFP rate validation, wrap-rate analysis, Agency BPA rate comparison, price-reasonableness memo, or fair-and-reasonable analysis. Build auditable Firm-Fixed-Price federal estimates using BLS OEWS wages, layered fringe/overhead/G&A/profit, GSA…
market-research-workflow
Trigger for: federal acquisition market research; FAR Part 10 reports; refreshing an existing market research report; analyzing commerciality, competition, small-business availability, contract type, consolidation, prior awards, vendors, or market conditions; or preparing supported findings for a Pre-Award Agent. A…
acquisition-policy-workflow
Trigger for: explaining current FAR, DFARS, or agency-supplement text; determining documented acquisition-policy status for an agency and FAR part; comparing codified text, RFO model text, and agency deviations; tracing acquisition rulemaking; finding procurement comment periods; analyzing public comments; refreshing…
govcon-growth-workflow
Trigger for: finding federal opportunities; capture and bid screening; competitor or incumbent intelligence; recompete pipelines; teaming partner research; agency, customer, or market intelligence; federal labor-rate or pricing context; or refreshing prior GovCon research. Always begin with the local SAM.gov…