lean

A low-token working mode for aicrew coding-agent skills. It keeps responses short and encourages reading only the parts of files needed for the task.

In plain words
What is it for?
Keeping agent sessions concise, searching or inspecting targeted file sections, reusing earlier summaries, and switching between lean and normal output with session commands.
Why use it?
It reduces unnecessary context use while preserving constraints, safety checks, technical details, and required pauses for user input.

Skill for Claude CodeCodex

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 skills/aksoftcode/aicrew/lean
Any agent
npx skills add AKSoftCode/aicrew --skill lean
Clone the repo
git clone --depth 1 https://github.com/AKSoftCode/aicrew

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 374 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 $0.00035 $0.00374
Opus 5 $0.00017 $0.00187
Sonnet 5 $0.00007 $0.00075
Haiku 4.5 $0.00003 $0.00037

Measured yesterday against content hash c6840e8c10f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

codex-skills/lean/SKILL.md · 45 lines

What it actually says

Caveman is default. This skill only matters if you switched to verbose with /normal or /lean off.

Lean (Codex)

Default for all aicrew Codex skills. Not opt-in.

Applies caveman output (~/Agents/agents/caveman.md) and context-economy reads (~/Agents/agents/context-economy.md) on every session unless the user disables with /normal or /lean off.

What lean mode does

  1. Keep answers terse and structured.
  2. Use diff/tree/search before reading full files.
  3. Prefer targeted slices over whole-file reads.
  4. Reuse prior summaries unless files changed.
  5. Keep correctness and safety constraints intact.

Session controls

  • /lean on — explicit boost or re-enable after disable
  • /normal or /lean off — verbose output and relaxed read policy

Safety and fidelity rules

  • Never drop constraints, invariants, acceptance criteria, or required warnings.
  • Keep technical strings verbatim: code, commands, paths, flags, URLs, errors, versions.
  • Interactive checkpoints: still pause and wait — never skip or fabricate answers.
  • If uncertain, ask one short clarifying question or state one explicit assumption.

When proposing changes, debugging, or reporting tests, include:

  • Tests: ran / not run
  • Assumptions: critical only
  • Risks: 1-3 bullets

Session resilience

When /session context is available, keep checkpoint updates in: .ai/state/AI_STATE.<tool>.<session>.md

Files

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.

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 · 45 lines · 35 tokens per session scan A c6840e8c10f1

Subscribe to this mod's changes

lean is a skill published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 374 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

sdd

Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.

liatrio-labs/spec-driven-workflow · 50 tokens

repo-layout

Register, resolve, and validate where a project's path-slots actually live via .layout-slots.yaml markers, so relocating a slot needs zero SKILL.md edits. Do NOT use for single-file lookups.

linkpranay-ai/context-engineering-protocol · 45 tokens

compiling-project-guidelines

Compile scattered guideline sources into one scope-aware COMPILED-GUIDELINES.md for other skills and ult-context-generate's Constraints layer. Do NOT use to enforce rules at runtime.

linkpranay-ai/context-engineering-protocol · 43 tokens

codegraph

Generate a codebase knowledge graph with graphify at graphify-out/ so other skills can query cross-file relationships before touching code. Do NOT use for runtime profiling.

linkpranay-ai/context-engineering-protocol · 40 tokens

institutional-memory-distill

Distill decisions, reasoning, and rejected alternatives from PRs, design docs, and postmortems into the project's decisionledger, so ult-context-generate's trip-wire can surface institutional memory before new work quietly repeats settled ground. Do NOT use to query the ledger against new work or decide…

linkpranay-ai/context-engineering-protocol · 89 tokens

vendored-skill

Vendored reference copy, for reproducibility of the consumer-benefit-user-stories case study. NOT part of this repo's installable skill set — origin: ground-up, maintained outside context-engineering-oss, in the same spirit as the FastAPI/Textual/Open5GS corpora this repo is demonstrated against rather than adopting.…

linkpranay-ai/context-engineering-protocol · 0 tokens