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 skills add drafthq/draft --skill integrationsgit clone --depth 1 https://github.com/drafthq/draftWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/drafthq/draft/integrations)<a href="https://agentmods.dev/skills/drafthq/draft/integrations"><img src="https://agentmods.dev/badge/skills/drafthq/draft/integrations/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/drafthq/draft/integrations"><img src="https://agentmods.dev/badge/skills/drafthq/draft/integrations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00028 | $0.00410 |
| Opus 5.5 | $0.00011 | $0.00164 |
| Sonnet 5.5 | $0.00006 | $0.00082 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
integrations 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 1mo 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.
What it actually says
Integrations Workflows
/draft:integrations is the canonical integrations parent command.
It handles connectors and exports to external systems like Jira.
Specialist integration workflows remain available as named modes:
/draft:jira preview(or/draft:integrations jira-preview)/draft:jira create(or/draft:integrations jira-create)
Step 1: Parse Intent and Route
Examine the user's input and route to the correct integrations workflow.
Explicit Named Modes
If the user explicitly invokes a specialist mode, route directly:
/draft:integrations jira-preview→ follow/draft:jira preview/draft:integrations jira-create→ follow/draft:jira create
Intent Routing
If no explicit mode is specified, infer the intent from the user's prompt:
| Intent | Action | Route |
|---|---|---|
| "Export to Jira", "Preview Jira issues", "Show me what you'll create in Jira" | Jira Preview | /draft:jira preview |
| "Create Jira issues", "Sync to Jira", "Make tickets" | Jira Create | /draft:jira create |
Step 2: Bare Parent Command Fallback
If the user runs a bare /draft:integrations without clear intent, present a small integrations menu with a recommended default path:
Draft Integrations Menu:
1. /draft:integrations jira-preview (Generate Jira export file for review)
2. /draft:integrations jira-create (Create Jira issues from export)
What integration action do you want to perform?
Do not automatically launch a specialist workflow without explicit or clear inferred intent.
Compatibility Note
The legacy specialist commands remain supported during the migration period, but /draft:integrations is the canonical parent for integration tasks.
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.
- 1mo ago First seen · 54 lines · 28 tokens per session scan A 84815b261e5e
integrations is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 12d ago), licensed MIT. It adds 28 tokens to every session and 410 once invoked, about $0.0001 per session on Opus 5.5. 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
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
skill-creator
Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.