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/getcrew44/crew44/discovery-processnpx skills add getcrew44/crew44 --skill discovery-processgit clone --depth 1 https://github.com/getcrew44/crew44What 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 | $0.00034 | $0.04545 |
| Opus 5 | $0.00017 | $0.02273 |
| Sonnet 5 | $0.00007 | $0.00909 |
| Haiku 4.5 | $0.00003 | $0.00455 |
Grade A, and why
discovery-process 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 2d 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Guide product managers through a complete discovery cycle—from initial problem hypothesis to validated solution—by orchestrating problem framing, customer interviews, synthesis, and experimentation skills into a structured process. Use this to systematically explore problem spaces, validate assumptions, and build confidence before committing to full development—avoiding "build it and they will come" syndrome and ensuring you're solving real customer problems.
This is not a one-time research project—it's a continuous discovery practice that runs in parallel with delivery, typically 1-2 discovery cycles per quarter.
Key Concepts
What is the Discovery Process?
The discovery process (Teresa Torres, Marty Cagan) is a structured approach to exploring problem spaces and validating solutions before building. It consists of:
- Frame the Problem — Define what you're investigating and why
- Conduct Research — Gather qualitative and quantitative evidence
- Synthesize Insights — Identify patterns, pain points, and opportunities
- Generate Solutions — Explore multiple solution options
- Validate Solutions — Test assumptions through experiments
- Decide & Document — Commit to build, pivot, or kill
Why This Works
- De-risks product decisions: Tests assumptions before expensive builds
- Customer-centric: Grounds decisions in real customer problems, not internal opinions
- Iterative: Builds confidence progressively through small experiments
- Fast learning: Discovers "no-go" signals early, saves wasted effort
Anti-Patterns (What This Is NOT)
- Not waterfall research: Discovery runs continuously, not once before dev
- Not user testing: Discovery validates problems; testing validates solutions
- Not a substitute for shipping: Discovery informs delivery, doesn't replace it
When to Use This
- Exploring new product/feature areas
- Investigating retention or churn problems
- Validating strategic initiatives before roadmap commitment
- Continuous discovery (weekly customer touchpoints)
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 505 lines · 34 tokens per session scan A af9642e3b3aa
discovery-process is a skill published in the GitHub repository getcrew44/crew44 (359 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 4,545 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…