agentic-context-engine: Skill for Claude Code

.claude/skills/kayba-pipeline/stage-6-hitl/SKILL.md

kayba-stage-6-hitl is a skill for Claude Code from kayba-ai/agentic-context-engine. It costs 87 tokens per session (2,435 once invoked), scanned A, original, Apache-2.0.

A human approval step for reviewing an action plan produced by the Kayba evaluation pipeline.

In plain words
What is it for?
It helps summarize evaluated insights, action types, discard reasons, and baseline measurements before recording the person's decision.
Why use it?
It gives a person enough evidence to approve, change, or reject proposed actions instead of accepting them automatically.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

This is kayba-ai/agentic-context-engine's own configuration. It tells Claude Code how to work on agentic-context-engine itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentic-context-engine configures →

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 · 2,565 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/stage-6-hitl/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.

agentmods badge for kayba-stage-6-hitl

README.md
[![agentmods](https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/stage-6-hitl/github.svg)](https://agentmods.dev/skills/kayba-ai/agentic-context-engine/stage-6-hitl)
Your own site
<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/stage-6-hitl"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/stage-6-hitl/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 kayba-stage-6-hitl

Your own site · 80×15
<a href="https://agentmods.dev/skills/kayba-ai/agentic-context-engine/stage-6-hitl"><img src="https://agentmods.dev/badge/skills/kayba-ai/agentic-context-engine/stage-6-hitl.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,435 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 warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 246
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.02435
Opus 5 $0.00044 $0.01218
Sonnet 5 $0.00017 $0.00487
Haiku 4.5 $0.00009 $0.00244

Measured 9d ago against content hash 394383c6c5ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kayba-stage-6-hitl 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.

.claude/skills/kayba-pipeline/stage-6-hitl/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stage 6: Human-In-The-Loop Gate

Present the action plan with enough context for an informed decision, collect the user's approval, and record the outcome.

The goal is not rubber-stamping. The user must receive enough information to genuinely evaluate, modify, or reject the plan -- even if they have not seen Stages 1-5.

Inputs

  • eval/action_plan.md -- the prioritized action plan from Stage 5
  • eval/baseline_metrics.md -- the evaluation rubric with baseline values
  • eval/baseline_metrics.json -- raw metric data (for exact numerator/denominator counts)
  • eval/stage1_insights_summary.md -- original insights (for trace evidence references)

Read all four files before starting.

Process

1. Build the executive summary

Compute and present the following counts from the action plan:

  • Total insights analyzed (raw count before deduplication)
  • Distinct actionable items after deduplication
  • Breakdown: prompt fixes, code fixes, discarded
  • Discard rate with one-line reason per discard (e.g., "5ac7f4ce: efficiency optimization, conflicts with turn discipline constraint")

Format:

EXECUTIVE SUMMARY
-----------------
Insights analyzed:    19 (raw) -> 12 distinct after dedup
Actionable:           9  (8 prompt fixes, 1 code fix)
Discarded:            3  (reasons listed below)

Discards:
  - 5ac7f4ce (Upfront Info Collection): conflicts with higher-priority turn discipline
  - fe2d51cb (Proactive Reservation Lookup): already default behavior, no failure evidence
  - 1fa1b826 (Cancellation Denial Enumeration): subsumed into cancellation checklist

2. Present the top 3 highest-impact changes

For each of the top 3 fixes by priority, present:

Before/after behavior -- use concrete examples from actual traces referenced in the insights. Quote the specific agent behavior that was wrong (before) and describe what the agent should do instead (after). Reference the trace task ID.

Target metric delta -- which metric(s) this fix targets, the current baseline value, and the expected direction. Do not fabricate precise target numbers. Use the format: "M1: 41.4% -> higher (target: 90%+)" only when the action plan provides a target; otherwise use "M1: 41.4% -> up".

Read the full file on GitHub · 259 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. 9d ago First seen · 259 lines · 87 tokens per session scan A 394383c6c5ad

Subscribe to this mod's changes

kayba-stage-6-hitl 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 87 tokens to every session and 2,435 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.

Related

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…

RamaAditya49/titen · 77 tokens

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…

browser-use/browser-use · 137 tokens

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.

bojieli/ai-agent-book · 27 tokens

mnemon

Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.

mnemon-dev/mnemon · 25 tokens

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).

zendev-sh/goai · 0 tokens

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.

GuyMannDude/mnemo-cortex · 44 tokens