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 agentmods add skills/felipecabargas/gambit/write-technical-briefnpx skills add felipecabargas/gambit --skill write-technical-briefgit 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/write-technical-brief)<a href="https://agentmods.dev/skills/felipecabargas/gambit/write-technical-brief"><img src="https://agentmods.dev/badge/skills/felipecabargas/gambit/write-technical-brief.svg" alt="Measured on agentmods" 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 | $0.00113 | $0.02555 |
| Opus 5 | $0.00056 | $0.01277 |
| Sonnet 5 | $0.00023 | $0.00511 |
| Haiku 4.5 | $0.00011 | $0.00255 |
Grade A, and why
write-technical-brief 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 4d 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 — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Brief Writer
When to Use
Use this skill when a feature has been specced and needs to be handed to engineering in a form they can act on. It adds the most value when:
- After an FR is written and ACs are verified — the feature request describes the problem and the expected outcomes; the technical brief translates that into what engineering needs to start work without ambiguity
- Before handing to engineering — prevents the classic "this spec has gaps" discovery mid-sprint by surfacing open questions while there is still time to resolve them with the PM
- When starting a sprint and realising the spec has gaps — if engineering finds unanswered questions during sprint planning, use this skill to structure those gaps and route them back to the PM quickly
- After a feature request authoring session — run this skill at the end of a
write-feature-requestsession to produce both the FR and the engineering handoff in a single workflow - When an existing spec needs a structured review — use this skill to audit a spec written without a template and surface what is missing before engineering reads it
Input Format
The skill works best with a Feature Request markdown document produced by the write-feature-request skill, but accepts any structured or unstructured spec. Provide one of the following:
A Feature Request markdown file (preferred):
Path: ./feature-requests/FR-0042-export-filters.md
A pasted FR description:
Feature: Saved Export Filters
Users need to save their filter configurations so they don't have to re-apply them
every time they export data. Filters include: date range, team, project, status.
ACs:
- Users can name and save a filter configuration
- Saved filters appear in a dropdown on the export screen
- Users can delete saved filters
- Filters are user-scoped (not shared across the team)
Optionally, existing technical notes or architecture context:
Current export system: server-side rendered, filters applied as query params.
No persistent filter storage exists today. Auth is session-based.
User settings currently stored in users table (PostgreSQL).
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.
- 4d ago First seen · 239 lines · 113 tokens per session scan A 16815b3acd4e
write-technical-brief is a skill published in the GitHub repository felipecabargas/gambit (2 stars, last pushed 3mo ago), licensed MIT. It adds 113 tokens to every session and 2,555 once invoked, about $0.0006 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
antigravity
Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle. Claude is the conductor/orchestrator — requirements, architecture, the hard 20%, verification, and review — and routes deterministic, high-volume work (scaffolding…
migrate-to-antigravity
Move an existing Claude Code setup onto the Antigravity CLI (agy) — user skills, CLAUDE.md, auto-memory, MCP servers, installed plugins, permissions and trusted workspaces. Use when the user says "migrate to Antigravity", "move my Claude Code config to agy", "bring my skills/memory/MCP over", "set up agy like my…
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…
meta-tags-optimizer
Optimize title tags, meta descriptions, Open Graph, and Twitter cards for maximum click-through rate. Generates multiple A/B test variations with character counting and SERP preview. Use when asked to "optimize title tag", "write meta description", "improve CTR", "Open Graph tags", "fix my meta tags", "social media…
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…
content-planner
GSC-driven content calendar. Pulls real Search Console data, finds the highest click-potential opportunities (striking-distance queries at positions 5-20, unanswered query intent, related-keyword expansions), and produces a dated, prioritized content calendar — ready to hand to /content-writer. Use when the user asks…