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/changenpx skills add drafthq/draft --skill changegit 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 | $0.00029 | $0.02357 |
| Opus 5 | $0.00015 | $0.01179 |
| Sonnet 5 | $0.00006 | $0.00471 |
| Haiku 4.5 | $0.00003 | $0.00236 |
Grade A, and why
change 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Course Correction
You are handling a mid-track requirement change using Draft's Context-Driven Development methodology.
Red Flags - STOP if you're
- Applying changes to spec.md or plan.md without showing the user what will change first
- Invalidating
[x]completed tasks without flagging them explicitly - Proceeding past the CHECKPOINT without user confirmation
- Editing files when the user said "no" or "edit"
Show impact before applying. Always confirm.
Step 0: Verify Draft Context
ls draft/tracks.md 2>/dev/null
If draft/ does not exist: STOP — "No Draft context found. Run /draft:init first."
Step 1: Parse Arguments
Extract from $ARGUMENTS:
- Change description — free text describing what needs to change (required)
- Track specifier — optional
track <id>prefix to target a specific track
Default Behavior
If no track <id> specified:
- Auto-detect the active
[~]In Progress track fromdraft/tracks.md - If no
[~]track, find the first[ ]Pending track - Display:
Auto-detected track: <id> - <name>before proceeding
If no change description provided:
- Error: "Usage:
/draft:change <description>or/draft:change track <id> <description>"
Step 2: Load Context
- Read
draft/tracks/<id>/spec.md— extract requirements and acceptance criteria - Read
draft/tracks/<id>/plan.md— extract all tasks with their current status ([ ],[~],[x],[!]) - Read
draft/tracks/<id>/metadata.json— for track type and status - Read
draft/tracks/<id>/hld.mdif present — extract Architecture, Detailed Design components, Dependencies, Checklist sections, and Approvals table (signed/unsigned) - Read
draft/tracks/<id>/lld.mdif present — extract Classes/Interfaces, Data Model, Algorithms, Error Handling sections
Step 3: Analyze Spec / HLD / LLD Impact
Analyze the change description against the loaded spec, HLD, and LLD.
Code-grounded impact (Ground-Truth Discipline G1, G2, G4): Classification ("Modified", "Unaffected", etc.) must be informed by the current code, not just the prior spec text. For each requirement / AC you're about to mark Unaffected, confirm the code path it depends on still behaves as the spec claims — Read the cited file or a representative file in the affected module before stamping Unaffected. Specs and implementations drift; "spec text unchanged" ≠ "behavior unchanged."
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 · 278 lines · 29 tokens per session scan A e9721cc12c41
change is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 13d ago), licensed MIT. It adds 29 tokens to every session and 2,357 once invoked, about $0.0001 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.