What is kayba-pipeline?

A seven-stage process for evaluating and improving an AI agent from saved trace files, which record the agent's actions and results. It analyzes those traces, defines measures and a review rubric, plans fixes, and can implement them.

Use it to run a full evaluation from a traces folder, gather domain context, define metrics, create a scoring rubric, plan corrections, and apply fixes with or without human approval.

It turns raw agent logs into a structured improvement cycle, with an optional human review pause before changes are made.

How kayba-ai/agentic-context-engine configures Claude Code

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 · 2,608 stars · on GitHub · kayba.ai

Reuse

Borrowing it

Nothing to install: this file belongs to kayba-ai/agentic-context-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/kayba-ai/agentic-context-engine/main/.claude/skills/kayba-pipeline/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/kayba-ai/agentic-context-engine

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/kayba-pipeline/github.svg)](https://agentmods.dev/skills/kayba-ai/agentic-context-engine/kayba-pipeline)

Your own site

<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/kayba-pipeline"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/kayba-pipeline/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/kayba-pipeline"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/kayba-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,442 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00091	$0.01442
Opus 5.5	$0.00036	$0.00577
Sonnet 5.5	$0.00018	$0.00288
Haiku 4.5	$0.00009	$0.00144

Measured 2mo ago against content hash 1f97e4a66b9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kayba-pipeline 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 2mo 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.

.claude/skills/kayba-pipeline/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kayba-pipeline

End-to-end pipeline: analyze traces → define metrics → build rubric → plan fixes → implement fixes.

Each stage is a separate skill file that can be run independently or as part of this pipeline.

Inputs

The user provides two things:

TRACES_FOLDER — path to a directory containing trace JSON files
HITL — true or false — whether to pause for human review before implementing fixes

If the user doesn't specify HITL, default to true (safe default).

Pipeline overview

┌─────────────────────────────────────────────────────────────────────┐
│  Stage 1: Kayba API Analysis        → skill: kayba-pipeline:stage-1-api-analysis   │
│  Stage 2: Domain Context Gathering  → skill: kayba-pipeline:stage-2-domain-context │
│  ─── stages 1 & 2 run in parallel ───                                              │
│  Stage 3: Metrics & Analysis        → skill: kayba-pipeline:stage-3-metrics        │
│  Stage 4: Rubric Definition         → skill: kayba-pipeline:stage-4-rubric         │
│  Stage 5: Action Plan               → skill: kayba-pipeline:stage-5-action-plan    │
│  Stage 6: HITL Gate                 → skill: kayba-pipeline:stage-6-hitl           │
│  Stage 7: Fix Implementation        → skill: kayba-pipeline:stage-7-fixer          │
└─────────────────────────────────────────────────────────────────────┘

Orchestration instructions

You are the orchestrator. Your job is to:

Create the eval/ directory and eval/pipeline_log.md
Spawn sub-agents that invoke stage skills via the Skill tool
Coordinate stage ordering and handle the HITL gate

Setup

Create eval/ directory and initialize eval/pipeline_log.md:

# Pipeline Log

| Stage | Name | Status | Started | Completed | Notes |
|-------|------|--------|---------|-----------|-------|
| 1 | Kayba API Analysis | pending | | | |
| 2 | Domain Context | pending | | | |
| 3 | Metrics & Analysis | pending | | | |
| 4 | Rubric Definition | pending | | | |
| 5 | Action Plan | pending | | | |
| 6 | HITL Gate | pending | | | |
| 7 | Fix Implementation | pending | | | |

Read the full file on GitHub · 146 lines

Files

What ships with it

7 files 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.

2mo ago First seen · 146 lines · 91 tokens per session scan A 1f97e4a66b9e

Subscribe to this mod's changes

kayba-pipeline is a skill published in the GitHub repository kayba-ai/agentic-context-engine (2,608 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,442 once invoked, about $0.0004 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 2026-08-30.

Analytics and metrics Building agents LLM Python agent-memory ai-agents ai-tools context-engineering

kayba-pipeline next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kayba-pipelinekayba-ai/agentic-context-engine	Skill	2.6k	1mo ago	Apache-2.0	A	91	Claude Code
browser-usebrowser-use/browser-use	Skill	120k	yesterday	MIT	A	57	Claude Code, Codex
x402browser-use/browser-use	Skill	120k	yesterday	MIT	A	175	Claude Code
remote-browserbrowser-use/browser-use	Skill	120k	yesterday	MIT	A	22	Claude Code
cloudbrowser-use/browser-use	Skill	120k	yesterday	MIT	A	177	Claude Code
open-sourcebrowser-use/browser-use	Skill	120k	yesterday	MIT	A	137	Claude Code
qabrowser-use/browser-use	Skill	120k	yesterday	MIT	C	103	Claude Code

agentic-context-engine: Skill for Claude Code