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.
git 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/agents/felipecabargas/gambit/discovery-to-fr)<a href="https://agentmods.dev/agents/felipecabargas/gambit/discovery-to-fr"><img src="https://agentmods.dev/badge/agents/felipecabargas/gambit/discovery-to-fr/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/agents/felipecabargas/gambit/discovery-to-fr"><img src="https://agentmods.dev/badge/agents/felipecabargas/gambit/discovery-to-fr.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 | $0.00112 | $0.01095 |
| Opus 5.5 | $0.00045 | $0.00438 |
| Sonnet 5.5 | $0.00022 | $0.00219 |
| Haiku 4.5 | $0.00011 | $0.00110 |
Grade A, and why
discovery-to-fr 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 1mo 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery to FR Agent
Overview
This agent is a chained workflow, not a standalone skill. It orchestrates three component skills in sequence to take raw user research all the way to a finished Feature Request — without requiring you to manage the handoffs between skills manually.
The three components and what each produces:
- synthesize-user-research — reads interview notes, survey data, support tickets, or other research inputs and produces a structured synthesis document covering key themes, pain points, and jobs-to-be-done (JTBD)
- build-user-persona — takes the synthesis output and constructs one or more named user personas with goals, frustrations, context, and behavioural patterns
- write-feature-request — takes the persona(s) and research insights as pre-loaded context and produces a complete, well-structured Feature Request with auto-generated acceptance criteria
Chain
synthesize-user-research → build-user-persona → write-feature-request
How It Runs
Step 1 — Synthesize Research
Run synthesize-user-research on the provided input (interview notes, survey responses, support tickets, or a description of what you have). The skill reads and structures the raw material into a synthesis document.
Save output as research-synthesis-[slug].md.
Present the key themes and JTBD to the user for a sanity check before proceeding. Ask: "Here are the main themes and jobs-to-be-done I found. Does this match your understanding of the research? Anything missing or wrong?"
Do not proceed to Step 2 until the user confirms.
Step 2 — Build User Persona
Run build-user-persona using the synthesis document as input. The skill constructs one or more named personas grounded in the research findings.
Save output as personas/[name].md.
Present the persona(s) to the user for confirmation. Ask: "Here is the persona I built from the research. Does this feel accurate? Should I adjust anything before using it to write the Feature Request?"
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.
- 1mo ago First seen · 91 lines · 112 tokens per session scan A 0fdc4653df40
discovery-to-fr is an agent published in the GitHub repository felipecabargas/gambit (2 stars, last pushed 4mo ago), licensed MIT. It adds 112 tokens to every session and 1,095 once invoked, about $0.0004 per session on Opus 5.5. 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 agents, from other repositories
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
elixir-way-architect
Synthesizes rewrite analysis and the ADR-000 compatibility bar into an idiomatic Elixir architecture, a complete mechanism ledger, ADRs and divergences. Use when /rewrite:architect has analysis and an accepted bar.
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.