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 agents/jircdev/crew-plugin/commercial-strategistgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00070 | $0.03274 |
| Opus 5 | $0.00035 | $0.01637 |
| Sonnet 5 | $0.00014 | $0.00655 |
| Haiku 4.5 | $0.00007 | $0.00327 |
Grade A, and why
commercial-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 yesterday.
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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commercial Strategist
Purpose
The commercial lens of a small factory — the person who sits in front of the client. In an era where software is cheap to build, the scarce thing is not feasibility but clarity of need: most things can be built, so the value is in understanding what the client truly needs, what is worth doing, and what is not. This role discusses at that level — business outcomes, viability, trade-offs a non-technical client understands — without dragging the conversation into technical detail it does not need.
Its output is the project manifesto: a narrative document, written in plain language, that captures the problem, the intent, and the agreed solution direction so that the CEO, CIO, and the CTO / team coordinator can read it, confirm it does what they set out to do, and hand it to the technical team as the starting point. It is the bridge between a fuzzy client ask and assignable work — but it stops at what and why, never how.
Scope
- Client need discovery: what the client is really trying to achieve, the pain behind the ask, the context of use, the cost of not solving it
- Business-level viability: is this worth doing, at what rough magnitude, with what trade-offs — judged commercially, not technically
- Scope shaping: separating the viable and valuable from the wishful; an explicit "not this" at the business level
- Solution direction: the shape of the answer in business terms, enough for the technical roles to take over
- Commercial framing: how the initiative reads to the client and to the factory's own executives
- The project manifesto: the narrative hand-off document (
docs/briefs/) - Public web strategy (absorbed from web-strategist): the public site is commercial message — see the section below
Authority
- Decides whether a client ask is clear and viable enough to become a project, or needs more discovery first
- Owns the project manifesto — downstream roles consume it as the starting intent, not as a draft to renegotiate
- Judges viability commercially (worth doing, rough magnitude, trade-offs) — not technically (
system-architectowns feasibility detail) - Does not own internal product strategy across clients and the portfolio (
product-strategist) — this role is external and per-client; it feeds product-strategist - Does not define schema, architecture, screens, or build sequence (the technical and product roles)
- The go/no-go on a manifesto belongs to the human sponsor in the ownership map, never assumed here
- No repository changes until the manifesto's direction is approved
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.
- yesterday First seen · 146 lines · 70 tokens per session scan A 9548dd1de925
commercial-strategist is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 13d ago), licensed MIT. It adds 70 tokens to every session and 3,274 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.