agentmods.dev

kb-lead

kb-lead is an agent for Claude Code from haowjy/creative-writing-skills. It costs 88 tokens per session (526 once invoked), scanned A, original, Apache-2.0.

An agent that records settled project knowledge in the appropriate documentation layers after work or a phase of work is complete. It gathers information from files and earlier sessions, writes the updates, and checks the result.

In plain words
What is it for?
Use it after a change settles to update the knowledge base, resolve documentation gaps, and record what the project learned.
Why use it?
It turns completed decisions and lessons into durable project knowledge instead of leaving them only in conversations or temporary work notes.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; names the NotebookEdit tool.

Part of the creative-writing-skills plugin — 28 skills, 5 agents shipped together

not rated 567repo +13 10d ago A scan 88 tokens original Apache-2.0

Good fit Use it after a change settles to update the knowledge base, resolve documentation gaps, and record what the project learned.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/haowjy/creative-writing-skills/kb-lead
View source ↗ haowjy/creative-writing-skills
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.

Clone the repo
git clone --depth 1 https://github.com/haowjy/creative-writing-skills

Made for: Claude Code.

Or install creative-writing-skills, the plugin that ships this one along with the rest of its 28 skills, 5 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 kb-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/haowjy/creative-writing-skills/kb-lead/github.svg)](https://agentmods.dev/agents/haowjy/creative-writing-skills/kb-lead)
Your own site
<a href="https://agentmods.dev/agents/haowjy/creative-writing-skills/kb-lead"><img src="https://agentmods.dev/badge/agents/haowjy/creative-writing-skills/kb-lead/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 kb-lead

Your own site · 80×15
<a href="https://agentmods.dev/agents/haowjy/creative-writing-skills/kb-lead"><img src="https://agentmods.dev/badge/agents/haowjy/creative-writing-skills/kb-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 88 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 526 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 $0.00088 $0.00526
Opus 5.5 $0.00035 $0.00210
Sonnet 5.5 $0.00018 $0.00105
Haiku 4.5 $0.00009 $0.00053

Measured 10d ago against content hash 4f9c3e1b2c05, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kb-lead 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 10d 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.

plugin/claude/agents/kb-lead.md · 43 lines

What it actually says

KB Lead

Capture what a settled change taught the project into its durable layers, following /creative-writing-skills:knowledge-layers resources/capture.md. You may be invoked mid-work, after a phase settles rather than after shipping: capture what settled; leave what is still moving.

You write every content update yourself. Spawn @explorer and @session-miner to read and mine; they do not write. @kb-maintainer owns within-tree structural work (splits, merges, renames, cross-refs) and never decides content truth; when it flags a contradiction, you resolve it. Spawn @cold-reader for the cold read of what you wrote.

Commit each version-controlled tree you touched; leave pushing to the caller. Report what you updated or that nothing needed adding, contradictions, gaps, and any repeated correction class, named as ready for /creative-writing-skills:correct.

Load these skills before starting, unless they are already in your context: /creative-writing-skills:shared-dao, /creative-writing-skills:knowledge-layers, /creative-writing-skills:qi-maintenance, /creative-writing-skills:llm-writing, /creative-writing-skills:information-hierarchy. Load these skills when the task fits: /creative-writing-skills:qi-layer, /creative-writing-skills:intent-modeling, /creative-writing-skills:shared-workspace, /creative-writing-skills:md-validation.

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. 10d ago First seen · 43 lines · 88 tokens per session scan A 4f9c3e1b2c05

Subscribe to this mod's changes

kb-lead is an agent published in the GitHub repository haowjy/creative-writing-skills (567 stars, last pushed 10d ago), licensed Apache-2.0. It adds 88 tokens to every session and 526 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 2026-10-28.

Memory and contextWriting and docs
Related

kb-lead compared with agents from other repositories

kb-lead next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
kb-leadhaowjy/creative-writing-skillsAgent56710d agoApache-2.0A88Claude Code
context-finderfuturegerald/futuregerald-claude-pluginAgent72d agononeA107Claude Code
wiki-ingestkarlorz/llm-wikiAgent5yesterdaynoneA64Claude Code
memory-curatorwbind-core/termpipe-mcpAgent04d agononeA45Claude Code
data scientistkhalilbenaz/MDANAgent023d agoMITA8Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code