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.
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.
curl -O https://raw.githubusercontent.com/kayba-ai/agentic-context-engine/main/.claude/skills/kayba-pipeline/stage-4-rubric/SKILL.mdgit clone --depth 1 https://github.com/kayba-ai/agentic-context-engineWrote 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/skills/kayba-ai/agentic-context-engine/stage-4-rubric)<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/stage-4-rubric"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/stage-4-rubric/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/skills/kayba-ai/agentic-context-engine/stage-4-rubric"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/stage-4-rubric.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.02015 |
| Opus 5 | $0.00039 | $0.01007 |
| Sonnet 5 | $0.00015 | $0.00403 |
| Haiku 4.5 | $0.00008 | $0.00201 |
Grade A, and why
kayba-stage-4-rubric 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stage 4: Rubric Definition
Organize metrics into a tiered evaluation rubric. Detect and resolve redundancy quantitatively. Ensure every insight is accounted for.
Inputs
eval/baseline_metrics.json— computed baseline values from Stage 3eval/compute_baselines.py— to understand what each metric measureseval/stage1_insights_summary.md— the original insightseval/stage2_domain_context.md— domain context
Read all four files before starting.
Process
1. Quantitative redundancy check
Before tiering, check every pair of metrics for overlap. Two metrics are redundancy candidates if ANY of the following hold:
- Denominator overlap >70%: compute
|denom_events(A) ∩ denom_events(B)| / min(|denom(A)|, |denom(B)|). If >0.70, they are candidates. To compute this, trace through the detector functions incompute_baselines.pyand determine which trace events (turns, calls, threads) each denominator iterates over. When denominators are identical sets (same loop, same filter), overlap is 100%. - Same skill set: the metrics map to the exact same set of insight/skill IDs from Stage 1.
- Logical subsumption: one metric's positive case is a strict subset of the other's (e.g., "turn has exactly 1 tool call" is a subset of "turn has no user-facing content alongside tool calls" only if every single-call turn also has no content — check this, don't assume it).
For each candidate pair, make an explicit decision with reasoning:
| Pair | Denom overlap | Skill overlap | Subsumption? | Decision | Reasoning |
|---|---|---|---|---|---|
| M1/M2 | 100% (same 29 turns) | identical | No — can violate one without the other | Keep both | Independently actionable: batching vs. content leaking are distinct fixes |
Valid decisions: keep both (with reasoning why they're independently actionable), merge (combine into one metric, specify how), or drop (specify which and why). "They feel different" is not sufficient reasoning — cite the specific behavior that one catches and the other misses.
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.
- 9d ago First seen · 164 lines · 77 tokens per session scan A 2a9452fdd706
kayba-stage-4-rubric is a skill published in the GitHub repository kayba-ai/agentic-context-engine (2,565 stars, last pushed 11d ago), licensed Apache-2.0. It adds 77 tokens to every session and 2,015 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
titen-memory
Use the Titen MCP server to recall bounded evidence-grounded context, record verified durable signals, submit feedback, and coordinate checkpoints, leases, or handoffs. Use when work may benefit from prior project memory or when a verified outcome should be preserved for another agent; do not use it to capture raw…
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.
goai
GoAI is a Go SDK for AI applications. One unified API across 25+ LLM providers. Inspired by the Vercel AI SDK, adapted to Go idioms (generics, interfaces, channels).
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.