A setting that controls whether Claude Code offers to save useful lessons from conversations to a project knowledge base.

Use it to enable or disable automatic knowledge-capture prompts. It also checks whether the project knowledge base has been initialized.

It avoids having to remember to capture important corrections, decisions, and practices manually. You can turn the automatic offer on or off in CLAUDE.md.

kb-auto — Skill for Claude Code by charlesjones-dev

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 charlesjones-dev/claude-code-plugins-dev --skill kb-auto

Clone the repo

git clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-dev

Made for: Claude Code.

Or install ai-knowledge, the plugin that ships this one along with the rest of its 17 skills.

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/charlesjones-dev/claude-code-plugins-dev/kb-auto/github.svg)](https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/kb-auto)

Your own site

<a href="https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/kb-auto"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/kb-auto/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/charlesjones-dev/claude-code-plugins-dev/kb-auto"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/kb-auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 453 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	$0.00024	$0.00453
Opus 5.5	$0.00010	$0.00181
Sonnet 5.5	$0.00005	$0.00091
Haiku 4.5	$0.00002	$0.00045

Measured 1mo ago against content hash db1a5ea15f61, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kb-auto 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 1mo 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.

plugins/ai-knowledge/skills/kb-auto/SKILL.md · 47 lines

What it actually says

Knowledge Base Auto-Capture Toggle

You are a knowledge base configuration assistant. Your job is to toggle the auto-capture instruction in CLAUDE.md that tells Claude Code to proactively offer learning capture.

Instructions

CRITICAL: This command MUST NOT accept any arguments. Ignore any text provided after the command.

Step 1: Check Current State

Read CLAUDE.md and find the Knowledge Base section.
If no Knowledge Base section exists, inform the user to run /kb-init first, then stop.
Check if the auto-capture instruction block already exists. Look for the marker comment .

Step 2: Toggle

If auto-capture is currently DISABLED (marker not found):

Add the following block immediately after the Knowledge Base table:

<!-- kb-auto: enabled -->
> **Auto-capture enabled**: At the end of each conversation, or when significant institutional knowledge, corrections, or best practices have been shared, proactively offer to run `/kb-learn` to capture learnings. Present a brief summary of what would be captured and ask the user if they'd like to save it before the conversation ends.

Inform the user:

"Auto-capture enabled. Claude will now offer to capture learnings at the end of conversations in this project."

If auto-capture is currently ENABLED (marker found):

Remove the entire auto-capture block (the marker comment and the blockquote instruction).

Inform the user:

"Auto-capture disabled. Claude will only capture learnings when you manually run /kb-learn."

Step 3: Confirm

Display the current state and remind the user:

Enabled: "Claude will proactively offer /kb-learn when conversations wrap up or when you share important knowledge. You'll always be asked to approve before anything is saved."
Disabled: "Run /kb-learn manually at the end of any conversation to capture learnings."

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.

1mo ago First seen · 47 lines · 24 tokens per session scan A db1a5ea15f61

Subscribe to this mod's changes

kb-auto is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (35 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 453 once invoked, about $0.0001 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.

Claude Code Git and workflow Memory and context ai claude developer-tools git-tools

git-ai-search

Search and restore AI conversation context from git history.

git-ai-project/git-ai · 13 tokens

remember

Save the decisions, facts, dead ends and architecture this conversation established to Atlas's shared memory, so other agents and future sessions can build on them.

pacifio/atlas · 32 tokens

release

Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.

matrixorigin/memoria · 27 tokens

recall-rationale

Recall why a past change was made by locating the Claude Code transcript that produced it. Use when the user asks to "recall the rationale", "find the rationale", "look up the rationale", "why did I do X", "why did we do X", "why was this changed", or "find the transcript for this commit".

tobihagemann/turbo · 74 tokens

release-finalizer

Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.

Fu-Jie/openwebui-extensions · 42 tokens

publish-no-version-bump

Commit and push code to GitHub, then publish to OpenWebUI official marketplace without updating version. Use when fixing bugs or optimizing performance that doesn't warrant a version bump.

Fu-Jie/openwebui-extensions · 40 tokens