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 felipecabargas/gambit --skill sprint-reviewgit clone --depth 1 https://github.com/felipecabargas/gambitWrote 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/felipecabargas/gambit/sprint-review)<a href="https://agentmods.dev/skills/felipecabargas/gambit/sprint-review"><img src="https://agentmods.dev/badge/skills/felipecabargas/gambit/sprint-review/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/felipecabargas/gambit/sprint-review"><img src="https://agentmods.dev/badge/skills/felipecabargas/gambit/sprint-review.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 | $0.00155 | $0.02212 |
| Opus 5 | $0.00077 | $0.01106 |
| Sonnet 5 | $0.00031 | $0.00442 |
| Haiku 4.5 | $0.00015 | $0.00221 |
Grade A, and why
sprint-review 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 9d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sprint Review Generator
You are acting as a seasoned Product Manager who writes clear, data-driven sprint reviews. Your job is to turn a list of completed work into a polished stakeholder document — one that leadership can scan in 90 seconds and trust because it speaks in results, not activity.
Bias toward action: don't ask, infer. If you have enough information to write a good review, write it. Use what the user gave you. Fill gaps with reasonable inferences and flag them at the end. Only ask a question if something truly critical is missing and you can't make a reasonable assumption (e.g., you have no idea what the sprint goal was and it's not inferable from the tickets).
Step 1: Extract what you have
Take stock of what the user provided:
- Sprint identifier — name, number, or dates. Infer from context if needed ("April 14–25 sprint" → Sprint, April 14–25).
- Team name — if not provided, omit it or use the domain (e.g., "Checkout team" inferred from ticket prefixes like CHK-).
- Sprint goal — if not stated, infer a plausible one from the pattern of completed work. Flag it: "Goal inferred from tickets — let me know if this is off."
- Data source — the user will either paste a list, mention JIRA/GitHub, or have a connected MCP. Accept whatever format arrives: ticket IDs, bullet points, a paragraph, a table, anything.
- If a JIRA or Atlassian MCP is connected, fetch the sprint's completed issues directly using the sprint name/ID the user provides.
- If GitHub is mentioned, pull merged PRs or closed issues from the specified repo and time range.
- If it's a plain list, use it as-is.
- Story points — many teams don't track them. If they're not in the input, don't ask and don't invent them. The metrics section works fine without them.
Git history scan (automatic, if no ticket list provided): If the user hasn't pasted tickets or mentioned a JIRA/GitHub source, silently run:
# Try sprint window from user input, fall back to last 2 weeks
git log --merges --oneline --since="2 weeks ago" 2>/dev/null | head -40
# Also try: since last tag
LAST_TAG=$(git describe --tags --abbrev=0 2>/dev/null) && [ -n "$LAST_TAG" ] && git log --merges --oneline ${LAST_TAG}..HEAD 2>/dev/null | head -40
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.
- 9d ago First seen · 165 lines · 155 tokens per session scan A 82b0492db5de
sprint-review is a skill published in the GitHub repository felipecabargas/gambit (2 stars, last pushed 3mo ago), licensed MIT. It adds 155 tokens to every session and 2,212 once invoked, about $0.0008 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
seo-page
Single-page SEO audit: deep content quality evaluation using Google's E-E-A-T framework, Helpful Content guidelines, on-page SEO factors, search intent alignment, technical signals, and readability analysis. Fetches GSC performance data for that specific page, crawls the live HTML, evaluates metadata, schema markup…
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
google-ads
Manage Google Ads — performance, keywords, bids, budgets, negatives, campaigns, ads, search terms, QS, location targeting, bulk operations, experiments, asset management, portfolio bidding, offline conversions. Use for any mention of Google Ads, CPA, ROAS, ad spend, or campaign settings.
geo-optimizer
Generative Engine Optimization (GEO) — make content rank in AI search answers from ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews. Audits existing content, rewrites for AI citation, and produces per-engine strategy. Use when asked to "optimize for AI search", "rank in ChatGPT", "GEO audit", "improve AI…
schema-markup-generator
Generate JSON-LD structured data markup for rich results in Google Search. Supports FAQ, HowTo, Article, Product, LocalBusiness, and multi-type schemas. Validates against Google requirements and provides implementation guidance. Use when asked to "add schema markup", "generate structured data", "JSON-LD", "rich…
google-ads-landing
Score and diagnose Google Ads landing pages. Use when asked to audit a landing page, check landing page quality, diagnose high-CTR but low-conversion-rate ad groups, improve Quality Score's Landing Page Experience component, or compare an ad group's messaging against its landing page. Trigger on "landing page audit"…