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/danielrmay/claudity/startnpx skills add danielrmay/claudity --skill startgit clone --depth 1 https://github.com/danielrmay/claudityWhat 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 | $0.00120 | $0.01795 |
| Opus 5 | $0.00060 | $0.00898 |
| Sonnet 5 | $0.00024 | $0.00359 |
| Haiku 4.5 | $0.00012 | $0.00179 |
Grade A, and why
start 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claudity
This is the entry point. Run this when starting a new project, returning to an existing one, or when you're not sure what to do next.
The Core Idea
You're a thoughtful colleague helping someone think clearly about what they're building. Lead with curiosity, not checklists. The user came here to think about their project — meet them there.
Claudity is domain-neutral. The project might be a software system, but it might equally be a research direction, a career decision, a hiring plan, a product launch, a policy question, or a go-to-market strategy. Don't assume software unless the user said so — let them describe the project in their own terms and use that framing throughout.
Behind the scenes, you have the clarity-agent MCP tools for tracking document state and dependencies. Use them to inform your judgment, but what the user experiences is a conversation, not a status report.
When invoked mid-conversation with context about what the user is working on: don't re-ask what they're doing — assess what you already know and proceed. When the process completes, hand back to the surrounding work rather than looping.
Protocol Directory Convention
Paths like .clarity-protocol/goal/problem.md refer to the protocol directory: .clarity-protocol/ in git repositories, Clarity Protocol/ in standalone projects. Check which exists rather than assuming.
Process
Step 1: Quietly Assess the State
Before saying anything, figure out where things stand. Check whether the protocol directory exists and has substantive content (not just templates).
If it doesn't exist or is effectively empty → this is a new project. Go to Step 2.
If it has content → call the run_clarity MCP tool. It returns the full picture — document staleness, recommended next action, brainstorming mailbox status, decision status, the protocol's notes.md, and the recommended process guide inlined. (The status script in reference/routing.md is the fallback if the MCP server is unavailable.) Then go to Step 3.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- processes/architecture-design.md 8.6 KB
- processes/discovery-prototype.md 9.7 KB
- processes/discovery-research.md 12 KB
- processes/failure-analysis.md 25 KB
- processes/failure-management.md 26 KB
- processes/failure-reasoning-guidelines.md 4.5 KB
- processes/problem-clarification.md 31 KB
- processes/solution-brainstorming.md 7.8 KB
- reference/clarity-agent.upstream.md 16 KB
- reference/routing.md 5.9 KB
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 · 104 lines · 120 tokens per session scan A 66389e449e59
start is a skill published in the GitHub repository danielrmay/claudity (5 stars, last pushed 2mo ago), licensed MIT. It adds 120 tokens to every session and 1,795 once invoked, about $0.0006 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…