gambit CLAUDE.md

gambit CLAUDE.md is an instructions file for coding agents from felipecabargas/gambit. It costs 599 tokens per session, scanned A, original, MIT.

A set of product-management instructions containing skills for planning, research, prioritisation, and team communication. It also defines workflows that chain several of these skills together.

In plain words
What is it for?
Checking acceptance criteria, writing feature requests and product strategies, reviewing sprints, ranking initiatives, analysing competitors, creating user personas, and synthesising user research.
Why use it?
It gives a coding agent repeatable guidance for turning product work into structured documents and decisions. This reduces the need to write the same planning process from scratch.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/felipecabargas/gambit/claude-md
Clone the repo
git clone --depth 1 https://github.com/felipecabargas/gambit

Wrote 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.

agentmods badge for gambit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/felipecabargas/gambit/claude-md.svg)](https://agentmods.dev/instructions/felipecabargas/gambit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/felipecabargas/gambit/claude-md"><img src="https://agentmods.dev/badge/instructions/felipecabargas/gambit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 599 This file is loaded in full into every session.
When invoked 599 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00599 $0.00599
Opus 5 $0.00300 $0.00300
Sonnet 5 $0.00120 $0.00120
Haiku 4.5 $0.00060 $0.00060

Measured 4d ago against content hash 3796901a3422, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gambit CLAUDE.md 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.

CLAUDE.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gambit

Provides thirteen product management skills and four chained workflow agents, available both as model-invoked skills and slash commands.

Available Skills

Core

  • verify-acceptance-criteria (/gambit:verify-acceptance-criteria) — evaluate AC quality against five dimensions
  • write-feature-request (/gambit:write-feature-request) — guided FR authoring with auto-generated ACs
  • write-product-strategy (/gambit:write-product-strategy) — generate product strategy documents
  • sprint-review (/gambit:sprint-review) — turn sprint data into stakeholder-ready reports
  • prioritize (/gambit:prioritize) — score and rank features or initiatives using RICE, ICE, or MoSCoW

Discovery

  • synthesize-user-research (/gambit:synthesize-user-research) — synthesize raw research into structured themes, pain points, and jobs-to-be-done
  • build-user-persona (/gambit:build-user-persona) — build evidence-backed user personas from research inputs
  • competitive-analysis (/gambit:competitive-analysis) — structure a competitive landscape analysis with player profiles and whitespace opportunities

Communication

  • write-okrs (/gambit:write-okrs) — generate well-structured OKRs derived from a product strategy
  • write-roadmap (/gambit:write-roadmap) — create a horizon-based product roadmap from strategy and OKRs
  • write-release-notes (/gambit:write-release-notes) — convert sprint tickets and PRs into customer-facing release notes
  • write-stakeholder-update (/gambit:write-stakeholder-update) — write a concise, data-led PM status update for leadership

Handoff

  • write-technical-brief (/gambit:write-technical-brief) — write an engineering handoff document from a verified Feature Request

Available Agents

  • discovery-to-fr (/gambit:discovery-to-fr) — end-to-end research-to-spec workflow: synthesize-user-research → build-user-persona → write-feature-request
  • fr-to-ready (/gambit:fr-to-ready) — feature-request-to-dev-ready workflow: write-feature-request → verify-acceptance-criteria → write-technical-brief
  • strategy-to-roadmap (/gambit:strategy-to-roadmap) — full strategy-to-execution workflow: write-product-strategy → write-okrs → write-roadmap
  • sprint-to-stakeholders (/gambit:sprint-to-stakeholders) — full sprint-to-communications workflow: sprint-review → write-release-notes → write-stakeholder-update

Read the full file on GitHub · 34 lines

Changes

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.

  1. 4d ago First seen · 34 lines · 599 tokens per session scan A 3796901a3422

Subscribe to this mod's changes

gambit CLAUDE.md is an instructions file published in the GitHub repository felipecabargas/gambit (2 stars, last pushed 3mo ago), licensed MIT. It adds 599 tokens to every session, about $0.0030 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.