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/dev)<a href="https://agentmods.dev/commands/aksoftcode/aicrew/dev"><img src="https://agentmods.dev/badge/commands/aksoftcode/aicrew/dev/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/dev"><img src="https://agentmods.dev/badge/commands/aksoftcode/aicrew/dev.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 | $0.00015 | $0.04473 |
| Opus 5.5 | $0.00006 | $0.01789 |
| Sonnet 5.5 | $0.00003 | $0.00895 |
| Haiku 4.5 | $0.00002 | $0.00447 |
Grade A, and why
dev 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.
How it starts
The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full 9-phase TDD pipeline for features, refactors, and any task that needs a design spec. Every phase stops for your explicit go-ahead.
Default output: caveman/lean — terse by default.
/normalor/lean offfor verbose. See~/Agents/agents/caveman.md.
⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE This pipeline contains checkpoints where Claude must pause and wait for your response. Checkpoints are marked "Wait for answer" or "Wait for confirmation".
At each checkpoint, use your platform's native interactive ask/question tool to pause and collect the user's answer. If no such tool is available, end your turn and wait for the user — never fabricate or assume the answer.
Known tools by platform (use if available):
Platform Checkpoint behavior Claude Code Call AskUserQuestiontool if available; otherwise end response and waitCursor Call askFollowupQuestiontool if available; otherwise end response and waitAntigravity Native ask tool if available; otherwise end response and wait Gemini CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitCodex CLI Native ask tool (e.g. ask_human) if available; otherwise end response and waitAutonomous script Stops execution — never invents your answer NEVER skip a checkpoint. NEVER fabricate the user's response.
Usage-limit resilience (state checkpoints) — mandatory
To survive unexpected usage timeouts, maintain a durable checkpoint file in the repo:
- Create or update a per-session file under:
.ai/state/ - File pattern:
.ai/state/AI_STATE.<tool>.<session>.md - Update it after every checkpoint and at the end of every phase.
- If filesystem write tools are unavailable, output the full
AI_STATE.mdcontent so the user can paste it into a file.
If /session was used, <tool> and <session> come from there. Otherwise use:
.ai/state/AI_STATE.unknown.unknown-<YYYY-MM-DD>-<HHMM>.md
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 · 441 lines · 15 tokens per session scan A 36486fb5711b
dev is a command published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 4,473 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
implement
Execute tasks from a track's implementation plan following TDD workflow.
test
Run TDD workflow — write failing tests, implement, verify. For bugs, use the Prove-It pattern.
spec-impl
Execute spec tasks using TDD methodology.
kiro-spec-impl
Command "kiro-spec-impl" from gotalab/cc-sdd, covering implementation task executor, core task, execution steps, step 1: load context and step 2: select tasks.
api-aqa-flow
Workflow for backend API test automation: TMS / Issue Tracker test cases → automated API tests, HITL-gated.
api-aqa-flow-test-case-specification
Phase 4 Test Case Specification of api-aqa-flow (HITL APPROVAL GATE).