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/drafthq/draft/tournpx skills add drafthq/draft --skill tourgit clone --depth 1 https://github.com/drafthq/draftWhat 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 | $0.00031 | $0.00647 |
| Opus 5 | $0.00015 | $0.00324 |
| Sonnet 5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
tour 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 3d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Tour: Interactive Onboarding
Provide an interactive codebase walk-through based on existing architecture and guardrail constraints.
Red Flags - STOP if you're
- Dumping the entire
architecture.mdinto the chat window. - Giving answers to foundational pattern questions before prompting the developer to guess.
- Explaining code the developer hasn't explicitly asked to view yet.
Execution Constraints
- Load Context: Read
draft/architecture.md,draft/tech-stack.md, anddraft/guardrails.md. - Interactive Cadence: Ask the developer if they are familiar with the tech stack constraints found in
draft/tech-stack.md. - Module Introduction: Instead of listing all modules, introduce the "Entry Point" module first.
- Active Challenge: After explaining a module's responsibility, challenge the developer: "Based on our Context-Driven Development rules, how do you think we handle data persistence here?" Wait for their answer before revealing the architecture strategy.
- If the answer is correct, confirm briefly and cite the supporting line in
architecture.md/guardrails.md. - If the answer is partially right, name what they got right, then ask a narrower follow-up (e.g., "Right that we cache reads — what's the invalidation trigger?") before revealing the rest.
- If the answer is wrong, do not just hand them the answer. Quote the specific guardrail or HLD section that contradicts it, then re-prompt with a hint scoped to that section.
- If the answer is correct, confirm briefly and cite the supporting line in
- Traceability: Highlight
draft/.state/facts.jsonshowing how module constraints have evolved. - Track Lifecycle Walk: Show the full feature lifecycle and who owns each gate:
/draft:new-track→spec.md(requirements + classification + approvers) +plan.md(phases/tasks)/draft:decompose→hld.md(always, with graph-derived diagrams) +lld.md(when --lld or High-complexity module)- Approvers (HLD): Technical Leads, Architecture Review Board, Cloud Operations (SaaS), QA Leads (on-prem), PM Leads
- Approvers (LLD): Team Leads, Technical Leads, Quality Assurance
/draft:implement→ TDD loop reading lld.md/hld.md for stub generation/draft:upload→ blocksgit uploadfor high/mission-critical tracks until HLD §Approvals signed/draft:deploy-checklist→ blocks deploy until HLD §Checklist + LLD §Alerting Thresholds populated- Walk a real example track from
draft/tracks/if any exist; otherwise sketch a hypothetical low-criticality flow.
- Completion: Guide the developer to create their first test track using
/draft:new-trackso they understand the artifact loop end-to-end.
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.
- 3d ago First seen · 40 lines · 31 tokens per session scan A d9fd9532ba6e
tour is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 15d ago), licensed MIT. It adds 31 tokens to every session and 647 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 2026-08-30.
Other skills, from other repositories
manim-composer
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization.…
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-orchestrate
Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.