kayba-ace

kayba-ace is a skill for Claude Code, Codex from kayba-ai/agentic-context-engine. It costs 0 tokens per session (1,154 once invoked), scanned A, original, Apache-2.0.

A script that learns from OpenClaw assistant session transcripts and writes an updated skillbook. A skillbook is a collection of learned guidance for handling future tasks.

In plain words
What is it for?
Use it to process new or selected JSONL session files, reprocess earlier sessions, write skillbook files, run a dry run, or enable Opik observability logging.
Why use it?
It turns past session records into reusable instructions instead of relying only on manually written improvements. It can also preview processing without making learning calls.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to process new or selected JSONL session files, reprocess earlier…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kayba-ai/agentic-context-engine/kayba-ace
About the project

Agentic Context Engine is an open-source engine that gives AI agents a persistent learning loop, helping them remember successful strategies and learn from failures across sessions. It is used to improve production agents, and also powers Kayba’s hosted service. Catalogue add-ons support workflows for operating and configuring the engine.

kayba-ai/agentic-context-engine · 2,564 stars · on GitHub · kayba.ai

Install

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.

Any agent
npx skills add kayba-ai/agentic-context-engine --skill kayba-ace
Clone the repo
git clone --depth 1 https://github.com/kayba-ai/agentic-context-engine

Made for: Claude Code, Codex.

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 kayba-ace

README.md
[![agentmods](https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/kayba-ace.svg)](https://agentmods.dev/skills/kayba-ai/agentic-context-engine/kayba-ace)
Your own site
<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/kayba-ace"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/kayba-ace.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,154 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.01154
Opus 5 $0.00000 $0.00577
Sonnet 5 $0.00000 $0.00231
Haiku 4.5 $0.00000 $0.00115

Measured 7d ago against content hash 33810fe8c542, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kayba-ace 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (learn_from_traces.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

examples/openclaw/kayba-ace/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ACE — Learn from Traces

This skill ships learn_from_traces.py, a script that reads OpenClaw session transcripts, feeds them through the ACE learning pipeline, and writes an updated skillbook to disk.

Usage

python learn_from_traces.py [OPTIONS] [FILES...]

The script auto-discovers new sessions from ~/.openclaw/agents/<agent>/sessions/ and only processes files that haven't been processed before. Processed filenames are tracked in ace_processed.txt.

Options

Flag Description
--dry-run Parse sessions but skip the learning step (no LLM calls)
--reprocess Ignore the processed log and reprocess all sessions
--agent ID OpenClaw agent ID (default: $OPENCLAW_AGENT_ID or main)
--output DIR Output directory for skillbook files (default: script directory)
--opik Enable Opik observability logging

Pass one or more JSONL file paths as positional arguments to process specific files instead of auto-discovering sessions.

Examples

Learn from all new sessions

python learn_from_traces.py

Discovers unprocessed sessions under ~/.openclaw/agents/main/sessions/, runs the learning pipeline, and writes the updated skillbook.

Dry run (no LLM calls)

python learn_from_traces.py --dry-run

Parses and validates sessions without calling the LLM. Useful for checking that session files are readable before committing to a full run.

Process a specific trace file

python learn_from_traces.py ~/.openclaw/agents/main/sessions/f967d602.jsonl

Skips auto-discovery and processes only the given file. The processed log is not updated when files are passed directly.

Process multiple files

python learn_from_traces.py session1.jsonl session2.jsonl session3.jsonl

Reprocess all sessions

python learn_from_traces.py --reprocess

Ignores ace_processed.txt and reprocesses every session file. Useful after upgrading ACE or when you want to rebuild the skillbook from scratch.

Read the full file on GitHub · 160 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 160 lines · 0 tokens per session scan A 33810fe8c542

Subscribe to this mod's changes

kayba-ace is a skill published in the GitHub repository kayba-ai/agentic-context-engine (2,564 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,154 tokens. 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 2026-08-30.