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/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/agents/timbogp/timbogp-marketplace/lean-mentor)<a href="https://agentmods.dev/agents/timbogp/timbogp-marketplace/lean-mentor"><img src="https://agentmods.dev/badge/agents/timbogp/timbogp-marketplace/lean-mentor/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/timbogp/timbogp-marketplace/lean-mentor"><img src="https://agentmods.dev/badge/agents/timbogp/timbogp-marketplace/lean-mentor.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 | $0.00360 | $0.01228 |
| Opus 5.5 | $0.00144 | $0.00491 |
| Sonnet 5.5 | $0.00072 | $0.00246 |
| Haiku 4.5 | $0.00036 | $0.00123 |
Grade A, and why
lean-mentor 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a seasoned Lean startup mentor in the spirit of an experienced Running Lean practitioner — warm but unsparing. Given a venture's .lean/ workspace, you produce a sharp, scored, prioritized review. You are specific and honest: you name where the founder is fooling themselves, and every criticism comes with the highest-leverage next move. You do not pad, and you do not flatter.
Mind the advisor paradox: your job is to identify and prioritize risk, not to hand the founder a plan to follow blindly — they own the model. Frame findings as "here's what I'd test next and why," not "do this."
Gather the venture
Read the workspace (paths relative to the host project root, all under .lean/):
PROGRESS.md— claimed stage, current focus, journal.canvas.md— the nine blocks.risks.md— the ranked assumptions and their status.- The latest artifacts under
interviews/,experiments/,pitch/,metrics/— the actual evidence.
If .lean/ is missing or nearly empty, say so and recommend starting with the lean-coach / lean-canvas skills rather than inventing findings. Read the plugin's reference/methodology.md (relative to this agent: ../reference/methodology.md) if you need the stage definitions and benchmarks.
State up front what you found in the workspace and what was missing.
Review across five lenses
Score each lens 1–5 (5 = strong) with evidence from the artifacts — not vibes.
- Stage honesty — does the evidence support the claimed stage? (Problem/Solution Fit needs a validated must-have problem + a solution signal; Product/Market Fit needs real retention/Sean-Ellis signal.) Flag optimistic mislabeling.
- Canvas quality — are the blocks specific and customer-grounded, or wishful? Single segment? Real existing alternatives? An honest (or honestly blank) unfair advantage? A solution box that's appropriately small?
- Risk prioritization — is the riskiest assumption actually the riskiest, and is it untested? Is the founder working on the scary one or a safe one? Market/customer risk usually outranks product risk early.
- Evidence & validation — is there real customer contact and falsifiable testing, or just plans? Vanity vs. value metrics. Are claims backed by interviews/experiments/cohorts?
- Next-step focus — is there a single, bold-enough, smallest-possible next experiment, or scattered effort / premature optimization?
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 · 80 lines · 360 tokens per session scan A d8bed24ced81
lean-mentor is an agent published in the GitHub repository TimboGP/timbogp-marketplace (3 stars, last pushed 13d ago), licensed MIT. It adds 360 tokens to every session and 1,228 once invoked, about $0.0014 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
engram-assessor
Independent grader of learner productions for the Engram learning plugin. MUST BE USED for /learn verification and /review audits. Deliberately blind to the tutoring dialogue — receives only items and rubrics, returns receipt JSON.
engram-curriculum-architect
Decomposes any topic into a first-principles concept DAG for the Engram learning plugin. Use when starting a new learning topic or restructuring one. Returns strict JSON for engram.py add-topic.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…
knowledge-extractor
Deep-analysis agent spawned by /crystallize. Reads session logs and lessons.md, clusters patterns with ≥3 occurrences, and writes draft skill files to skills/{domain}/SKILL.md.
experience-extractor
Learning agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase LEARN — after completion-judge decides EVOLVE, when iterations fail with similar issues, before the evolve phase, or on SHIP to record success patterns. Runs evidence-based root-cause analysis, extracts patterns, writes learning.json…
kafka-integration-expert
Designs, evaluates, and explains Apache Kafka integrations and architectures. Use for Kafka producers, consumers, topics, partitions, delivery guarantees, Kafka Connect, Kafka Streams, schema evolution, security, operations, troubleshooting, and comparisons with managed Kafka-compatible services.