agentic-jujutsu

agentic-jujutsu is a command for Claude Code from frankxai/agentic-creator-os. It costs 0 tokens per session (757 once invoked), scanned B, original, Apache-2.0.

A learning layer that records agent sessions, finds repeated successful workflows, and uses them to suggest approaches for future tasks.

In plain words
What is it for?
Use it to track operations and failures, discover workflow patterns, and restore learned context when sessions start.
Why use it?
It helps the system retain useful patterns across sessions and share them between agents working together.

Command for Claude Code

Written for Claude Code: SessionStart hook event.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .claude-flow/hooks/learning-hooks.sh stats.

Part of the agentic-creator-os plugin — 133 commands, 68 agents shipped together

Good fit Use it to track operations and failures, discover workflow patterns, and restore learned context when sessions start.

Compare 6 commands from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/frankxai/agentic-creator-os
agentmods
npx agentmods add commands/frankxai/agentic-creator-os/agentic-jujutsu

Made for: Claude Code.

Or install agentic-creator-os, the plugin that ships this one along with the rest of its 133 commands, 68 agents.

Wrote 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.

agentmods badge for agentic-jujutsu

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/agentic-creator-os/agentic-jujutsu/github.svg)](https://agentmods.dev/commands/frankxai/agentic-creator-os/agentic-jujutsu)
Your own site
<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.

agentmods 80×15 button for agentic-jujutsu

Your own site · 80×15
<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>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 757 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.00757
Opus 5 $0.00000 $0.00378
Sonnet 5 $0.00000 $0.00151
Haiku 4.5 $0.00000 $0.00076

Measured 6d ago against content hash 960ebfdd43d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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
.claude/commands/agentic-jujutsu.md · 91 lines

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:

  1. Trajectory Tracking: Every session records what operations happened, in what order, and whether they succeeded
  2. Pattern Discovery: After 3-5 sessions, patterns emerge (e.g., "deployment always follows these 7 steps")
  3. AI Suggestions: Before starting a task, get recommendations based on past successful workflows
  4. 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.

Read the full file on GitHub · 91 lines

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. 6d ago First seen · 91 lines · 0 tokens per session scan B 960ebfdd43d9

Subscribe to this mod's changes

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.