Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osnpx agentmods add commands/frankxai/agentic-creator-os/agentic-jujutsuWrote 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/frankxai/agentic-creator-os/agentic-jujutsu)<a href="https://agentmods.dev/commands/frankxai/agentic-creator-os/agentic-jujutsu"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/agentic-jujutsu/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/frankxai/agentic-creator-os/agentic-jujutsu"><img src="https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/agentic-jujutsu.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 | $0.00000 | $0.00757 |
| Opus 5 | $0.00000 | $0.00378 |
| Sonnet 5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade B, and why
agentic-jujutsu scanned grade B with 1 finding 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 6d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat .claude/trajectories/patterns.json | python3 -m json.tool How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agentic Jujutsu - ACOS Self-Learning Engine
The learning backbone of ACOS. Based on ruvnet's agentic-jujutsu (v2.3.6, MIT), customized for ACOS.
What It Does
Agentic Jujutsu is the self-learning layer that makes ACOS smarter over time:
- Trajectory Tracking: Every session records what operations happened, in what order, and whether they succeeded
- Pattern Discovery: After 3-5 sessions, patterns emerge (e.g., "deployment always follows these 7 steps")
- AI Suggestions: Before starting a task, get recommendations based on past successful workflows
- Multi-Agent Memory: When swarm agents work in parallel, they share patterns without conflicts
How It's Integrated Into ACOS
You don't need to run anything manually. It's embedded in the hook pipeline:
| Hook | What Jujutsu Does |
|---|---|
| SessionStart | Creates trajectory, loads learned patterns, restores learning state |
| PostToolUse | Records each operation to the active trajectory |
| PostToolUseFailure | Records failures (low-quality patterns) for future avoidance |
| Stop | Finalizes trajectory, auto-scores success, extracts new patterns |
Status Check
# View trajectory stats (how many sessions learned from)
bash .claude-flow/hooks/learning-hooks.sh stats
# View discovered patterns
cat .claude/trajectories/patterns.json | python3 -m json.tool
# View learning metrics
cat .claude-flow/metrics/learning-status.json | python3 -m json.tool
Current Learning State
When invoked, read and display:
.claude/trajectories/- count completed trajectories.claude/trajectories/patterns.json- show discovered patterns.claude-flow/metrics/learning-status.json- show learning metrics
Manual Operations (Advanced)
Most users never need these. The hooks handle everything automatically.
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.
- 6d ago First seen · 91 lines · 0 tokens per session scan B 960ebfdd43d9
agentic-jujutsu is a command published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 757 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
meta-learn
Capture post-session learnings and compound intelligence across skills.
meta-synthesis
Detect cross-skill patterns and propose brain updates.
build-brain
Build or update your GTM brain — product context, ICP, positioning, voice, market context, and proof points.
brief-me
Get briefed — loads your full memory, pulls live state from all connected tools, surfaces risks, staleness, upcoming milestones, and gives you a prioritized briefing so you're never starting blank.
retro
Run a post-ship retrospective — measure outcomes vs. predictions, extract lessons, update memory, and feed insights back into the PM system.
onboarding
Set up PM Copilot — a guided wizard that builds your persistent memory profile so every future session is grounded in your product context.