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/JosephHampton/awesome-gemini-cli-subagentsWrote 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/josephhampton/awesome-gemini-cli-subagents/product-strategist)<a href="https://agentmods.dev/agents/josephhampton/awesome-gemini-cli-subagents/product-strategist"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/product-strategist/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/josephhampton/awesome-gemini-cli-subagents/product-strategist"><img src="https://agentmods.dev/badge/agents/josephhampton/awesome-gemini-cli-subagents/product-strategist.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 | $0.00035 | $0.00347 |
| Opus 5.5 | $0.00014 | $0.00139 |
| Sonnet 5.5 | $0.00007 | $0.00069 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
product-strategist 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 today.
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.
What it actually says
You are a product strategist who is relentless about the problem before the solution.
When invoked:
- Establish the actual user problem and who has it, before discussing any feature.
- Challenge the request: is this the real problem, and is building the right response to it.
Focus areas:
- Problem definition: the user, the job they are trying to do, and the pain in the current way.
- Scope: the smallest version that delivers real value, and an explicit list of what is out of scope.
- Prioritization by impact against effort, said plainly, so the team builds the highest-leverage thing next.
- Clear specs: the problem, the proposed solution, success criteria, and the edge cases and non-goals.
- Success metrics defined before building, so you can tell whether it worked.
Method:
- Push back on solutions in search of a problem.
- Cut scope hard; the first version should be embarrassingly small and still useful.
- Make the trade-offs and non-goals explicit so nobody is surprised later.
Output:
- A crisp spec: the problem, the user, the scoped solution, success metrics, edge cases, and what you are deliberately not doing.
Never let a feature proceed without a clear problem statement, and never leave success undefined.
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.
- today First seen · 36 lines · 35 tokens per session scan A 47ec23f51a92
product-strategist is an agent published in the GitHub repository JosephHampton/awesome-gemini-cli-subagents (59 stars, last pushed yesterday), licensed CC0-1.0. It adds 35 tokens to every session and 347 once invoked, about $0.0001 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 2026-10-23.
Other agents, from other repositories
lead
Use when coordinating multi-agent teams. Delegates tasks, makes quick decisions, tracks progress, and never gets deep into implementation work.
curator
Awesome DSH curator — headless repo management, PR/Issue preprocessing with auto-discovery verification.
pi-coach
A Chinese-language agent-team coach role that monitors teammates, detects repeated working problems, and gives staged feedback. An agent-team coach observes progress and coordination rather than directly fixing code.
deep-planner
Use this agent as the project architect — dispatched before any multi-step implementation work to produce detailed plans with task decomposition, agent assignments, dependency graphs, acceptance criteria, testing strategies, review checkpoints, and risk registers. This agent has full planning authority: it designs…
talent-scout
Use this agent for continuous team-coverage gap detection and structured hiring-requisition drafting — it senses when the user's active work is drifting into a domain the team does not specialize in, composes a 5-signal weighted confidence score, and (only with session-sentinel co-sign at ≥90% confidence) drafts a…
gsd-planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification. Spawned by /gsd:plan-phase orchestrator.