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/vladolaru/claude-code-plugins/knowledge-capturenpx skills add vladolaru/claude-code-plugins --skill knowledge-capturegit clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWhat 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 | $0.00035 | $0.04639 |
| Opus 5 | $0.00017 | $0.02320 |
| Sonnet 5 | $0.00007 | $0.00928 |
| Haiku 4.5 | $0.00003 | $0.00464 |
Grade A, and why
knowledge-capture 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 — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Capture Skill
Shared logic for all /dex:* commands. Follow these procedures exactly - do what the calling command asks, nothing more.
Project Discovery
Discover the project's knowledge infrastructure fresh on every invocation. Scan the filesystem directly - no config files, no cached state.
Discovery Steps
- Find the project root: Run
git rev-parse --show-toplevel - Find the instructions file: Check in order, use the first found:
<root>/CLAUDE.md<root>/.claude/CLAUDE.md<root>/AGENTS.md- a direct AGENTS.md project (e.g. a Codex-only repo with no CLAUDE.md). Use it as the instructions file withai_dir=.ai, then skip the CLAUDE.md indirection in step 3a.
- Resolve instructions file and
ai_dir: a. If a CLAUDE.md was found, check whether it redirects to AGENTS.md:- Symlink: Run
readlink <claude_md_path>. If the target filename isAGENTS.md, use the symlink target. - Include directive: Read the file content. If the entire content is a single
@AGENTS.mdline (with optional whitespace/newlines), find the referenced AGENTS.md relative to CLAUDE.md's directory. - If no indirection is detected, continue using CLAUDE.md.
b. Derive
ai_dirfrom the resolved instructions file: - CLAUDE.md →
ai_dir=.claude - AGENTS.md →
ai_dir=.ai
- Symlink: Run
- Find knowledge directory: Check for
<root>/<ai_dir>/docs/- Migration check: If
ai_diris.aibut<root>/.ai/docs/does not exist and<root>/.claude/docs/does exist, flag a migration mismatch. Use.claude/docs/as the active knowledge directory for now, but record the mismatch forinitandstatusto surface.
- Migration check: If
- List existing subdirectories: Check for
learnings/,patterns/,decisions/,research/within the knowledge directory - Count lines: Run
wc -lon the resolved instructions file
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 · 504 lines · 35 tokens per session scan A 9cda1664eb62
knowledge-capture is a skill published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 5d ago), licensed MIT. It adds 35 tokens to every session and 4,639 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…