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/igor/braindead/project-workspace-skillnpx skills add igor/braindead --skill project-workspace-skillgit clone --depth 1 https://github.com/igor/braindeadWhat 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 | $0.00000 | $0.00815 |
| Opus 5 | $0.00000 | $0.00407 |
| Sonnet 5 | $0.00000 | $0.00163 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
project-workspace-skill 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Workspace Setup
Create a project-specific .claude/CLAUDE.md file for Brain Dead vault projects.
Invocation
User says: /project-workspace or mentions setting up a project workspace
What This Skill Does
Creates a standardized .claude/CLAUDE.md file for project-specific workspaces within the Brain Dead vault. The file:
- References back to Brain Dead vault rules (frontmatter, PARA, RAG)
- Includes project-specific context (client, deliverables, timeline)
- Enables focused workspace while maintaining vault methodology
Detection & Intelligence
- Check current directory - Verify we're within Brain Dead vault
- Infer project name - Extract from path (e.g.,
1. Projects/ClientX/→ "ClientX") - Ask minimal questions:
- Client name (if not obvious from path)
- Brief project scope
- Active deliverables (optional)
- Timeline (optional)
Template Structure
The created .claude/CLAUDE.md follows this pattern:
# Project: [Client Name] - [Project Name]
## Project Context
- **Client**: [Name]
- **Scope**: [Brief description]
- **Active deliverables**: [List if provided]
- **Timeline**: [If provided]
## Vault Context
**This project is part of Brain Dead vault** - all Brain Dead vault rules apply:
- **PARA organization**: Files created here belong to the vault structure
- **Frontmatter requirements**: See `brain dead/.claude/agent_docs/yaml-frontmatter.md` for mandatory fields
- **RAG collections available**: Full vault searchable (braindead, readwise, 2025_portfolio, whatsapp)
- **Client archiving**: When complete, archive to `4. Archive/Clients/[Year]/[Client]/`
## Quick Links
- Vault root: `brain dead/`
- Project files: [inferred path]
- RAG operations: See global CLAUDE.md
## Notes
[Space for project-specific notes, constraints, or reminders]
Workflow
- User invokes skill
- Detect current working directory
- Verify it's within
brain dead/structure - If in
1. Projects/[Name]/, infer project name from path - Ask questions using AskUserQuestion:
- Client name (prefill with inferred name if available)
- Brief project scope
- Optionally: deliverables, timeline
- Create
.claude/directory if needed (mkdir -p) - Write
.claude/CLAUDE.mdwith filled template - Confirm creation with path
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 · 101 lines · 0 tokens per session scan A 86254f489542
project-workspace-skill is a skill published in the GitHub repository igor/braindead (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 815 tokens. 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…