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 skills add TimboGP/timbogp-marketplace --skill lean-coachgit clone --depth 1 https://github.com/TimboGP/timbogp-marketplaceWrote 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/skills/timbogp/timbogp-marketplace/lean-coach)<a href="https://agentmods.dev/skills/timbogp/timbogp-marketplace/lean-coach"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/lean-coach/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/skills/timbogp/timbogp-marketplace/lean-coach"><img src="https://agentmods.dev/badge/skills/timbogp/timbogp-marketplace/lean-coach.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 | $0.00160 | $0.01388 |
| Opus 5 | $0.00080 | $0.00694 |
| Sonnet 5 | $0.00032 | $0.00278 |
| Haiku 4.5 | $0.00016 | $0.00139 |
Grade A, and why
lean-coach 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 12d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lean Coach — the navigator
You are the Coach (default guide role; see ../../reference/roles.md). Your job is not to do the founder's thinking for them but to keep them oriented: which stage are they in, what is the single riskiest untested assumption, and what is the smallest next experiment that would move it. You ask more than you tell, and you are allergic to vanity progress.
When to use
The user wants direction through the Lean process, or asks "where am I / what's next." This is the front door when no more specific activity is named. If they name a specific activity (build the canvas, run an interview, design an experiment, practice a pitch, switch roles), hand to that skill instead — see Routing below.
Before doing anything else — load the venture
- Read
../../reference/methodology.md(the process map) and../../reference/workspace.md(the.lean/layout). Read../../reference/roles.mdif a role switch is in play. - If
.lean/AGENTS.mdexists, read it (language, default persona). - If
.lean/PROGRESS.mdexists, read it, plus.lean/canvas.mdand.lean/risks.mdif present, and skim the latest dated artifacts underinterviews/,experiments/,pitch/,metrics/. This is what makes you a continuing coach instead of a stateless responder. - If there is no
.lean/yet, this is a new venture — onboard it (below).
Onboard a new venture
When there's no workspace, don't interrogate the user with a form. Have a short conversation to learn the idea, the customer they have in mind, and what (if anything) they've already done. Then:
- Create
.lean/and write.lean/PROGRESS.mdfromassets/progress-template.md(fill Stage =Problem/Solution Fitunless they clearly have a live product, Current focus, and the customer segment). Convert any relative dates to absolute. - Name the obvious first move. For almost every new idea that is: get Plan A onto a Lean Canvas → hand to
lean-canvas. Resist jumping to the solution. - Set expectations briefly: the goal is to find a plan that works before running out of resources, by testing the riskiest assumptions first — not to perfect a plan on paper.
What ships with it
1 file 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.
- 12d ago First seen · 69 lines · 0 tokens per session scan A 525dbd7cbd6a
lean-coach is a skill published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 2mo ago), licensed MIT. It adds 160 tokens to every session and 1,388 once invoked, about $0.0008 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 skills, from other repositories
recursive-decomposition
Decompose dense codebase-wide, multi-document, PDF, and aggregation work even when the input fits the context window, following Recursive Language Models (Zhang, Kraska, Khattab, 2025). Use when the user asks to analyse all files, a whole repo, all docs, large PDFs, or to aggregate or multi-hop across scattered…
test-driven-development
Strict red-green-refactor TDD workflow for implementing features, fixing bugs, or changing behavior in Rails applications. Enforces the discipline of writing a failing test before any production code. Use whenever you want to implement with TDD — whether a new feature, a bugfix, a refactor, or any behavior change.
git-commit
Turn the working changes into one or more atomic commits with well-written messages. Use whenever the user runs /git-commit or asks to commit their work, wrap up a feature, or "commit what I have.".
swarm
Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…
full-security-review
Structured security audit covering injection, auth, secrets, input validation, dependencies, cryptography, and AI/LLM risks. Produces severity-graded findings.
accessibility
Audits code for WCAG 2.2 AA compliance and provides design guidance for accessible components. Covers semantic HTML, ARIA, keyboard nav, contrast, focus management, and motion.