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/implementnpx skills add drafthq/draft --skill implementgit 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 | $0.00043 | $0.07900 |
| Opus 5 | $0.00022 | $0.03950 |
| Sonnet 5 | $0.00009 | $0.01580 |
| Haiku 4.5 | $0.00004 | $0.00790 |
Grade A, and why
implement 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 — 853 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Track
Implement tasks from the active track's plan following the TDD workflow.
/draft:implement is the canonical implementation parent.
It owns the common execution loop and absorbs three adjacent commands when appropriate:
/draft:status/draft:coverage/draft:revert
Red Flags - STOP if you're
- Implementing without an approved spec and plan
- Skipping TDD cycle when workflow.md has TDD enabled
- Marking a task
[x]without fresh verification evidence - Batching multiple tasks into a single commit
- Proceeding past a phase boundary without running the three-stage review
- Writing production code before a failing test (when TDD is strict)
- Assuming a test passes without actually running it
Verify before you mark complete. One task, one commit.
Constraints
Draft skills are designed for single-agent, single-track execution. Do not run multiple Draft commands concurrently on the same track.
Parent Contract
/draft:implement owns four execution jobs:
- Build the next task → baseline
/draft:implement - Show current execution state →
/draft:status - Measure implementation completeness via coverage →
/draft:coverage - Undo implementation safely →
/draft:revert
Most developers should only need /draft:implement in the common path.
Explicit Child Modes
If the user invokes explicit child intent, route directly:
/draft:implement status→ follow/draft:status/draft:implement coverage→ follow/draft:coverage/draft:implement revert→ follow/draft:revert
Examples:
/draft:implement status/draft:implement coverage src/auth/draft:implement revert phase 2
Explicit child mode always wins over the baseline implementation workflow.
Bare /draft:implement
Without an explicit child mode, /draft:implement should:
- continue the active track's next task
- surface blocked-task conditions immediately
- run review and verification gates at phase boundaries
- suggest or attach coverage only when the implementation state justifies it
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 · 853 lines · 43 tokens per session scan A e6be3eb3eb51
implement is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 7,900 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
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.