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.
npx agentmods add commands/aksoftcode/aicrew/concludegit clone --depth 1 https://github.com/AKSoftCode/aicrewWhat 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 | $0.00014 | $0.01126 |
| Opus 5 | $0.00007 | $0.00563 |
| Sonnet 5 | $0.00003 | $0.00225 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
conclude 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-of-session wrap-up — saves learnings to project memory and proposes a commit message.
Default output: caveman/lean — terse by default.
/normalor/lean offfor verbose. See~/Agents/agents/caveman.md.
⚠️ INTERACTIVE CHECKPOINTS — MANDATORY RULE
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.
/conclude — Session Conclusion + Memory Capture
Wrap up this development session. Summarize what was done and capture any non-obvious project learnings into the persistent memory system.
Step 1: Session Summary
Generate a concise summary:
- Main task accomplished this session
- Run
git diff --name-only HEAD— list the files that changed - Test status (did all pass?)
- Any known remaining issues or follow-ups
Present this to the user clearly.
Step 2: Check the session journal
Look for the session journal written by the Stop hook:
~/.claude/projects/[project-slug]/memory/session_journal.md
Where [project-slug] is the current working directory with / replaced by - and leading - stripped.
If the journal exists, read the most recent entries (last 3–5) for context about what the hook captured.
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.
- yesterday First seen · 134 lines · 14 tokens per session scan A 8df7962eaa20
conclude is a command published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 1,126 once invoked, about $0.0001 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.
Other commands, from other repositories
tutorial
Interactive tutorial for learning the plugin. Walks through agents, skills, hooks, and commands with hands-on examples.
mentor
Educational mode that explains concepts, teaches patterns, and guides learning. Ideal when learning a new codebase, technology, or programming concept.
consolidate
Dream cycle -- promote patterns, prune stale, reconcile contradictions, optionally promote to global.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
learn
Command "learn" from chohra-med/expo_boilerplate, covering command: learn — the learning loop (feedback → rules), when to run it, invocation, the loop (6 steps) and 1 — capture.
learn
Learn Claude Code best practices and capture lessons into persistent memory.