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 commands/studiokjm/ai-harness-template/leangit clone --depth 1 https://github.com/studioKjm/ai-harness-templateWrote 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/commands/studiokjm/ai-harness-template/lean)<a href="https://agentmods.dev/commands/studiokjm/ai-harness-template/lean"><img src="https://agentmods.dev/badge/commands/studiokjm/ai-harness-template/lean.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00929 |
| Opus 5 | $0.00000 | $0.00464 |
| Sonnet 5 | $0.00000 | $0.00186 |
| Haiku 4.5 | $0.00000 | $0.00093 |
Grade A, and why
lean 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 4d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/lean — Lean MVP Hypothesis Manager
Methodology: lean-mvp
Purpose: Build→Measure→Learn cycle. One metric. Pivot or persist.
Usage
/lean new --title <title> [--statement <text>] [--metric <name>] [--target <threshold>]
[--window <days>] [--story <id>] [--tags <tag1,tag2>]
/lean build <hyp-id> [--mvp <description>] [--metric <name>] [--target <value>]
/lean measure <hyp-id> --actual <value> [--source <data-source>]
/lean decide <hyp-id> persist|pivot|abandon --rationale <text> [--decided-by <name>]
/lean status <hyp-id>
/lean list [--state proposed|testing|measuring|decided]
/lean link <hyp-id> [--story <id>] [--rfc <id>] [--tdd <id>] [--parent <id>]
State Machine
new
↓
💡 proposed ──build──→ 🔨 testing ──measure──→ 📏 measuring
│
decide
┌──────┴──────┐
persist pivot / abandon
│ │
✅ decided 💡 new hypothesis
Key invariant: decided requires metric_actual to be populated.
A pivot creates a new hypothesis via --next-hyp.
Workflow
1. Define the hypothesis
python3 methodologies/lean-mvp/scripts/lean.py new \
--title "email-nudge-increases-retention" \
--statement "We believe that a 3-day re-engagement email will increase 30-day retention by 5% for inactive users" \
--metric "30d_retention_rate" \
--target "> 40% (currently 35%)" \
--window 14
2. Build the MVP
# After shipping minimal feature:
python3 methodologies/lean-mvp/scripts/lean.py build hyp-20260430-001 \
--mvp "3-day inactive user email with personalized content"
3. Collect data
# After measurement window closes:
python3 methodologies/lean-mvp/scripts/lean.py measure hyp-20260430-001 \
--actual "38.2%" \
--source "Mixpanel 30d retention report"
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.
- 4d ago First seen · 109 lines · 0 tokens per session scan A b2bf44801346
lean is a command published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 929 tokens. 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 commands, from other repositories
VibeGuard: ExecPlan
Long-term task execution plan — generates self-contained execution documents from SPEC, supports cross-session recovery.
VibeGuard: Review
Structured code review - first run the guard to obtain the baseline, then review according to security → logic → quality → performance priority.
VibeGuard: Live Truth
Verify live claims with fresh facts, inferences, and unresolved gaps.
capture-feedback
Quick feedback capture with structured signals.
check-gates
Run a Pre-Action Gate check against prevention rules before executing a risky action.
harness-adopt
Apply Harness Starter Kit to the current target repository with the prompt-first adoption workflow.