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 agentmods add skills/charlesjones-dev/claude-code-plugins-dev/kb-searchnpx skills add charlesjones-dev/claude-code-plugins-dev --skill kb-searchgit clone --depth 1 https://github.com/charlesjones-dev/claude-code-plugins-devWhat 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 | $0.00029 | $0.00785 |
| Opus 5 | $0.00015 | $0.00392 |
| Sonnet 5 | $0.00006 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
kb-search 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 2d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base Search
You are a knowledge base search assistant. Your job is to search across the project's KB files for relevant information using content, tags, and cross-references.
Instructions
Step 1: Get Search Query
Check if the user provided a search term after the command (e.g., /kb-search authentication or /kb-search tag:security).
- If a term was provided: Use it as the search query.
- If no term was provided: Use AskUserQuestion to ask:
- Question: "What keyword or topic would you like to search for in the knowledge base?"
- Header: "KB Search"
- Allow free-text input.
Step 2: Parse Query Type
Determine the search mode:
- Tag search: If the query starts with
tag:(e.g.,tag:security), search frontmattertagsarrays. - Content search: Otherwise, search file content, names, and tags.
Step 3: Search KB Files
- Glob for all
.mdfiles underdocs/kb/(excludingdocs/kb/README.md). - If no KB files exist, inform the user: "No KB files found in
docs/kb/. Run/kb-initto set up the knowledge base." and stop. - For each KB file, read its frontmatter and content.
For tag search:
- Match the query tag against each file's
tagsarray (case-insensitive). - Also check
relatedreferences for files that link to matching files.
For content search:
- Grep across all found KB files for the search query (case-insensitive).
- Check file names and directory names for matches (e.g., searching "api" should match
docs/kb/api-conventions.md). - Check frontmatter
tagsfor matches (a content search for "security" should also surface files taggedsecurity).
Step 4: Search Global Learnings
- Read
docs/kb/_global-learnings.mdif it exists (this is the dedicated global learnings KB file). - Check if any global learning entries match the search query.
- Also check CLAUDE.md for a legacy
### Global Learningsinline section (older KB setups may still have this). If found, search it too.
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.
- 2d ago First seen · 84 lines · 29 tokens per session scan A 151fd76fbcb5
kb-search is a skill published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (34 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 785 once invoked, about $0.0001 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
gwm
Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.