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.
npx skills add charlesjones-dev/claude-code-plugins-dev --skill kb-listgit clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-devWrote 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/charlesjones-dev/claude-code-plugins-dev/kb-list)<a href="https://agentmods.dev/skills/charlesjones-dev/claude-code-plugins-dev/kb-list"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/kb-list/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/charlesjones-dev/claude-code-plugins-dev/kb-list"><img src="https://agentmods.dev/badge/skills/charlesjones-dev/claude-code-plugins-dev/kb-list.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 | $0.00030 | $0.00816 |
| Opus 5.5 | $0.00012 | $0.00326 |
| Sonnet 5.5 | $0.00006 | $0.00163 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
kb-list 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base Listing
You are a knowledge base inventory assistant. Your job is to display the current state of the project's knowledge base. This is a read-only operation - no files are modified.
Instructions
CRITICAL: This command MUST NOT accept any arguments. Ignore any text provided after the command.
Step 1: Read CLAUDE.md
- Read the project's
CLAUDE.mdfile. - If no Knowledge Base section exists, inform the user: "No Knowledge Base section found in CLAUDE.md. Run
/kb-initto set one up." and stop. - Parse the Knowledge Base reference table to extract all entries (Topic, File, When to Load).
- Read
docs/kb/_global-learnings.mdif it exists for global learnings count. Also check for a legacy### Global Learningsinline section in CLAUDE.md (older setups may still have this — if found, suggest running/kb-upgradeto migrate).
Step 2: Verify File Status and Read Frontmatter
For each entry in the table:
- Check if the referenced file actually exists using Glob or Read.
- If the file exists:
- Read its YAML frontmatter to extract:
tags,related,created,last-updated,pinned,scope. - Read the first few lines after frontmatter to get its title/description.
- Mark as OK.
- Flag if frontmatter is missing or incomplete (NEEDS FRONTMATTER).
- Read its YAML frontmatter to extract:
- If the file doesn't exist, mark as MISSING.
Step 3: Scan for Orphaned Files
- Glob for all
.mdfiles underdocs/kb/(excludingdocs/kb/README.md). - Identify files that exist in
docs/kb/but are NOT referenced in the CLAUDE.md table. - Mark these as UNREGISTERED. Read their frontmatter if present.
Step 4: Display Summary
Present the results in a clear format:
Knowledge Base Status
=====================
Registered KB Files:
| Status | Topic | File | Tags | Last Updated | Pinned | When to Load |
|--------|-------|------|------|-------------|--------|--------------|
| OK | API Conventions | docs/kb/api-conventions.md | api, rest | 2026-04-01 | No | `packages/api/**` — api, rest |
| OK | Auth Rules | docs/kb/auth.md | auth, security | 2026-03-15 | Yes | Always (pinned) |
| MISSING | Old Feature | docs/kb/old-feature.md | - | - | - | — feature-x |
| NEEDS FM | Deployment | docs/kb/deployment.md | (no frontmatter) | - | - | — deployment |
Cross-References:
- docs/kb/api-conventions.md → [[auth]]
- docs/kb/auth.md → [[api-conventions]]
Unregistered Files (in docs/kb/ but not in CLAUDE.md):
- docs/kb/new-topic.md (tags: misc, workflow)
Global Learnings: {count} entries
Summary: {ok_count} registered, {missing_count} missing, {unregistered_count} unregistered, {no_frontmatter_count} missing frontmatter
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 · 71 lines · 30 tokens per session scan A a5782d88594d
kb-list is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (35 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 816 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.
Other skills, from other repositories
git-ai-search
Search and restore AI conversation context from git history.
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.
release
Cut a Memoria release. Version bump, CHANGELOG, CI workflows, Docker image. Use when publishing a new version.
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".
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.
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.