lean-promote

A command that prepares a Lean-Track project for Full-Track development by creating a promotion brief and archiving Lean documents. Lean-Track is a short cycle for testing an idea; Full-Track is the more complete development process.

In plain words
What is it for?
Use it when the Lean results support continued development, or when a project needs to move into Full-Track after a mid-cycle decision.
Why use it?
It carries the useful findings into the next phase without moving the code to another repository. It also records which existing modules should be kept, refactored, or rebuilt.

Command

Install

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.

agentmods
npx agentmods add commands/jonase47/ccpr/lean-promote
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,680 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01680
Opus 5 $0.00000 $0.00840
Sonnet 5 $0.00000 $0.00336
Haiku 4.5 $0.00000 $0.00168

Measured yesterday against content hash 88ed923d1956, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lean-promote 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.

commands/lean-promote.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/lean-promote – Promote Lean → Full-Track via Promotion Brief

Creates docs/PROMOTION_BRIEF.md as a structured bootstrap input for /project-init. Archives Lean artifacts (FRAME, LEARNINGS, CLAUDE-lean) to docs/lean-archive/. Code stays in the same repo; Full-Track decides per module: keep / refactor / rebuild.

Argument: $ARGUMENTS = [optional: projectdir]

  • Without argument: operates on $(pwd).

Prerequisites

  • docs/FRAME.md exists
  • docs/LEARNINGS.md exists AND decision: promote OR a mid-flight promotion trigger has fired
  • docs/TRACK_DECISION.md exists
  • Code baseline is committable (clean working tree recommended)
  • Template: ~/.claude/templates/PROMOTION_BRIEF_TEMPLATE.md

Lead Agent

konzeptor for content consolidation, project-planner for catch-up obligations and Backlog proposals.

Execution

1. Prerequisites Check

  • If docs/FRAME.md or docs/LEARNINGS.md is missing → STOP with a note indicating which skill must run first.
  • If LEARNINGS.md decision is not promote AND no mid-flight trigger was specified → ask: "Which promotion trigger? (PROMOTE / mid-flight-1..5)" — for mid-flight, request a rationale.
  • Code baseline: git status — if the working tree is dirty, ask for user confirmation.
  • Capture commit SHA via git rev-parse HEAD for frontmatter.

2. Read Materials

Load:

  • docs/FRAME.md (all 8 sections)
  • docs/LEARNINGS.md (hypothesis check, what works / does not work, surprises)
  • docs/TRACK_DECISION.md (most recent entry — prerequisites, Knockouts, Indicators)
  • docs/CONSTITUTION.md if applicable (if Lean already extended it)

3. Derive PROMOTION_BRIEF Sections

Consolidate — not a plain copy, but a condensed synthesis:

1. Validated Findings (from LEARNINGS "what works" + confirmed hypothesis check) → Per finding: concrete statement + 1-line evidence note.

2. Confirmed Assumptions (from FRAME section 7 "risk assumptions → what must work" — those that held) → Each tagged with Full-Track phase: → relevant for P0-problem | P1-features | P3-techstack | …

Read the full file on GitHub · 144 lines

Changes

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.

  1. yesterday First seen · 144 lines · 0 tokens per session scan A 88ed923d1956

Subscribe to this mod's changes

lean-promote is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,680 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 2026-08-31.