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 derekrbreese/fantasy-football-skills --skill keeper-evaluationgit clone --depth 1 https://github.com/derekrbreese/fantasy-football-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/derekrbreese/fantasy-football-skills/keeper-evaluation)<a href="https://agentmods.dev/skills/derekrbreese/fantasy-football-skills/keeper-evaluation"><img src="https://agentmods.dev/badge/skills/derekrbreese/fantasy-football-skills/keeper-evaluation/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/derekrbreese/fantasy-football-skills/keeper-evaluation"><img src="https://agentmods.dev/badge/skills/derekrbreese/fantasy-football-skills/keeper-evaluation.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 | $0.00102 | $0.02132 |
| Opus 5 | $0.00051 | $0.01066 |
| Sonnet 5 | $0.00020 | $0.00426 |
| Haiku 4.5 | $0.00010 | $0.00213 |
Grade A, and why
keeper-evaluation 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keeper Evaluation
Rank keeper candidates by surplus value: what the player is worth minus what keeping them costs. A good keeper is one priced below market, not simply the best player on the roster.
Step 1: Load context
Read leagues.md from the project root first — the fields that matter here are keeper rules (how many, cost mechanism, escalation), teams, scoring, and starting slots. If the file is missing or keeper rules aren't recorded, ask: How many keepers? What does keeping a player cost (a draft round, an auction dollar amount)? Does the cost escalate year over year? Then offer to save the answers back to leagues.md. If more than one league is defined, use the one marked (default) unless the user names another.
Step 2: Gather candidates and price them
For each candidate: player, keeper cost (round or $), and current ADP or auction market value. For round-cost leagues, get the exact pick the keep consumes: draft slot, round, and the league's collision rule if multiple keepers map to the same round. If the league has eligibility restrictions (tenure limits, drafted-only, no first-rounders, tag deadlines, etc.), screen those out before doing surplus math. Ask the user to supply these, or — if browser automation is available and they're logged in — read current values off their platform or a rankings site, stating the source and date.
Live platform source routing. Honor a browser the user explicitly names. If leagues.md records a Preferred browser, use that when it has a signed-in session for the platform. Otherwise use any authenticated browser the current assistant already has. For Yahoo league data, prefer an authenticated browser over a connector. If a Yahoo connector returns 403, unauthorized, or an equivalent authorization failure, do not retry it during the same task. For non-Yahoo platforms, use a purpose-built connector when it is available and returns complete current data; otherwise use the browser. Read league rosters, the free-agent pool, standings, transaction history, and any rankings site directly instead of making the user paste them. Timestamp live data and name the source. The session rules from roster-ops apply unchanged: the user's session is the auth; never ask for, read, store, or type credentials; use the visible UI rather than platform endpoints; and stop and hand back on any login, 2FA, captcha, consent, or unusual-activity screen. If no usable live source exists, state the access gap and do not fabricate league-specific analysis.
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 · 76 lines · 102 tokens per session scan A c4693cef92e0
keeper-evaluation is a skill published in the GitHub repository derekrbreese/fantasy-football-skills (4 stars, last pushed 28d ago), licensed MIT. It adds 102 tokens to every session and 2,132 once invoked, about $0.0005 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
technical-documentation
Audit, write, and improve developer documentation using Google's Developer Documentation Style Guide and Technical Writing courses. Use this skill for any documentation work, even when the user names no style guide: "audit our docs", "review this README", "write a README", "getting started guide", "how-to or…
top-design
Create award-winning, immersive web experiences at the level of Awwwards-featured agencies. Use when the user mentions "Awwwards quality", "make my site stunning", "scroll animations", "parallax storytelling", "cinematic web design", "portfolio site", or "brand experience". Also trigger when elevating a standard…
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
design-sprint
Run a structured 5-day process to prototype, test, and validate product ideas with real users. Use when the user mentions "design sprint", "validate before we build", "rapid prototype", "test with users", or "should we build this". Also trigger when a team is stuck in endless debate over a high-stakes product…
improve-retention
Diagnose and fix retention problems using behavior design (B=MAP). Use when the user mentions "users sign up but dont stick around", "activation rate", "onboarding friction", "retention metrics", "why users dont complete", "churn analysis", or "aha moment". Also trigger when analyzing cohort retention curves…
steve-jobs-design-review
Review designs, products, and features with Steve Jobs' standards: ruthless simplicity, focus, and end-to-end excellence. Use when the user mentions "Steve Jobs review", "design review", "product review", "what would Steve do", "insanely great", "this feels too complicated", "too many features", "product taste"…