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/plannpx skills add drafthq/draft --skill plangit 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 | $0.00060 | $0.00605 |
| Opus 5 | $0.00030 | $0.00302 |
| Sonnet 5 | $0.00012 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
plan 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 yesterday.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan - Planning & Architecture Router
/draft:plan is the consolidated entry point for all planning and upfront architecture work in the Context-Driven Development lifecycle.
When to Use
- Starting a new feature, bug fix, or refactor track
- Decomposing large modules or changes into dependency-aware units
- Recording Architecture Decision Records (ADRs)
- Cataloging and prioritizing technical debt
- Handling mid-track requirement or scope changes
Routing Logic
The router parses intent from natural language and dispatches to the correct leaf skill. Ambiguous requests surface a short menu of options.
| User Intent Keywords | Dispatches To | Purpose |
|---|---|---|
| new feature, new track, start X, add Y, plan a refactor, fix the Z bug | /draft:new-track |
Collaborative spec + plan creation for track |
| decompose, break into modules, dependency map | /draft:decompose |
Module decomposition + graph |
| adr, architecture decision, record decision, design decision | /draft:adr |
ADR authoring and evaluation |
| tech debt, technical debt, catalog debt, debt analysis | /draft:tech-debt |
6-dimension debt scan + prioritization |
| change, scope changed, requirements changed, update spec, mid-track pivot | /draft:change |
Structured change impact & plan update |
Dispatch Examples
User: "start a new feature for user profile editing"
→ dispatches to /draft:new-track "user profile editing"
User: "decompose the payment module"
→ dispatches to /draft:decompose "payment module"
User: "document our decision to use event sourcing"
→ dispatches to /draft:adr "Use event sourcing for order processing"
User: "find and prioritize our technical debt"
→ dispatches to /draft:tech-debt
User: "the requirements changed, we need to support multi-tenancy now"
→ dispatches to /draft:change "add multi-tenancy support"
Relationship to Primary Workflow
/draft:plan augments but does not replace the core /draft:new-track and /draft:implement flow. Many planning activities are launched via /draft:plan for discoverability, then flow into the primary track lifecycle.
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.
- yesterday First seen · 61 lines · 60 tokens per session scan A a507cd40d48e
plan is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 13d ago), licensed MIT. It adds 60 tokens to every session and 605 once invoked, about $0.0003 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
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.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.