lean-frame

A command that creates a compact source of truth for a project being tested in Lean-Track. It records the problem, hypothesis, risks, and related working guidance in FRAME.md and CLAUDE-lean.md.

In plain words
What is it for?
Use it to start or revise a Lean-Track frame after the project has been assigned to that track, including its problem, hypothesis, and risk assumptions.
Why use it?
It keeps the essential direction in a small set of documents instead of spreading it across a larger conception process. This makes the testable idea and its risks easier to follow.

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-frame
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 1,408 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 $0.01408
Opus 5 $0.00000 $0.00704
Sonnet 5 $0.00000 $0.00282
Haiku 4.5 $0.00000 $0.00141

Measured yesterday against content hash 6694581c8d4c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lean-frame 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-frame.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/lean-frame – Create Lean-Track Single-Source-of-Truth

Creates or revises docs/FRAME.md (Single-Source-of-Truth of the Lean-Track) and docs/CLAUDE-lean.md (slim project CLAUDE for Lean mode). Replaces the entire P0+P1+P3 conception work in the Lean-Track with a compact single-screen document.

Argument: $ARGUMENTS = [optional: projectdir]

  • No argument: operates on $(pwd).

Prerequisites

  • docs/TRACK_DECISION.md exists and specifies current_track: lean (otherwise: run /track-decision first)
  • Templates: ~/.claude/templates/FRAME_TEMPLATE.md, ~/.claude/templates/CLAUDE_LEAN_TEMPLATE.md

Lead Agent

konzeptor with system-architekt for tech-stack guidance.

Execution

1. Prerequisites check

If docs/TRACK_DECISION.md is missing or current_track: full → STOP with note: "Lean-Track not active. Run /track-decision first."

If docs/FRAME.md already exists → Re-Frame mode: load the existing FRAME as base, ask per section "keep / change".

2. Collect FRAME sections interactively

Ask interactively (keep it brief — Lean is not P0 depth):

  1. Problem (1–2 sentences): Which problem, for whom?
  2. Hypothesis (1 sentence): What do we believe the prototype will prove or disprove?
  3. Demo-Audience (3–5 people / personas): Who tests it, how does feedback flow?
  4. MVP-Scope (max. 5 bullets in + max. 5 bullets deliberately out)
  5. Tech-Stack (3–5 lines, with a brief rationale per choice)
  6. Constitution-Light (3–5 hard constraints for this prototype — e.g. "no PII", "local only", "no auth")
  7. Risk assumptions:
    • What can fail? (list)
    • What must work without fail? (make-or-break)

Note on section 6: If Constitution-Light wants to grow beyond 5 bullets → offer: "Should I call /constitution and create a full docs/CONSTITUTION.md? FRAME will then reference it."

3. Embed promotion triggers

Copy the 5 promotion triggers from docs/TRACK_DECISION.md into section 8 of the FRAME (or from the template default if TRACK_DECISION does not contain them).

Read the full file on GitHub · 122 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 · 122 lines · 0 tokens per session scan A 6694581c8d4c

Subscribe to this mod's changes

lean-frame 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 1,408 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.