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/AKSoftCode/aicrewWrote 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/aksoftcode/aicrew/lean)<a href="https://agentmods.dev/commands/aksoftcode/aicrew/lean"><img src="https://agentmods.dev/badge/commands/aksoftcode/aicrew/lean/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/commands/aksoftcode/aicrew/lean"><img src="https://agentmods.dev/badge/commands/aksoftcode/aicrew/lean.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 | $0.00020 | $0.00324 |
| Opus 5.5 | $0.00008 | $0.00130 |
| Sonnet 5.5 | $0.00004 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00032 |
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 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.
What it actually says
Caveman is default. These commands only matter if you toggled verbose with
/normalor/lean off.
/lean
Default: already terse/lean (caveman output + context-economy reads). See ~/Agents/agents/caveman.md.
Usage:
/lean on— amplify lean mode for the rest of this session (re-enables if/normalor/lean offwas used)/lean off— disable lean mode and return to normal verbose behavior (aka/normal)
Aliases: /terse = /lean on (deprecated alias, kept for backward compat); /normal = /lean off.
Lean mode combines:
- Terse output with no filler
- Diff/tree/search before file reads
- Slice reads instead of whole-file reads when possible
- Reuse of prior summaries unless a file changed
- Compact context between major phases
Always preserve verbatim:
- Code blocks
- Commands
- File paths
- Flags
- URLs
- Error text
- Version numbers
Never omit:
- Constraints and invariants
- Required warnings
- Edge cases that affect correctness
- Acceptance criteria
- Interactive checkpoint pauses
When proposing changes, debugging, or reporting tests, add a short footer:
- Tests: ran / not run
- Assumptions: critical only
- Risks: 1–3 bullets
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 · 45 lines · 20 tokens per session scan A d374360ff59c
lean is a command published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 3mo ago), licensed MIT. It adds 20 tokens to every session and 324 once invoked, about $0.0001 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 commands, from other repositories
demo-consume-context
Worked example: discover, load, and tag an approved context package, then write a reverse-index addendum. Proves the produce/consume/tag loop end-to-end. Not for real feature work.
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…
gaai-ask
Search workspace memory — ranked entries with 1-hop graph context (cognitive guarantee).
headroom
Headroom status — proxy, memory, and token savings.
vault
Build/refresh a unified Obsidian vault (knowledge + all repo wikis).
gaai-bootstrap
Initialize or refresh project context via Bootstrap Agent.