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 jiragit 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/jira)<a href="https://agentmods.dev/skills/drafthq/draft/jira"><img src="https://agentmods.dev/badge/skills/drafthq/draft/jira/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/jira"><img src="https://agentmods.dev/badge/skills/drafthq/draft/jira.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 78 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Memory Poisoning · line 189 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00020 | $0.05311 |
| Opus 5.5 | $0.00008 | $0.02124 |
| Sonnet 5.5 | $0.00004 | $0.01062 |
| Haiku 4.5 | $0.00002 | $0.00531 |
Grade A, and why
jira 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.
How it starts
The opening of the file, as written. The whole thing — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jira
Single entry point for all Jira workflows: preview Draft tracks as Jira issues, create them via MCP (default = 1 Story per track; --epic = 1 Epic + 1-3 Stories), and review any Jira ticket (epic, story, bug, sub-task) end-to-end.
Subcommand Routing
Parse $ARGUMENTS and dispatch:
| User Intent | Subcommand | Behavior |
|---|---|---|
(no args), preview, preview <track-id> |
preview (default) | Generate jira-export-<timestamp>.md — one Story containing all phases/tasks |
preview --epic ... |
preview --epic | Generate rich export: 1 Epic + 1–3 Stories (max) |
create, create <track-id> |
create | Create 1 Story (default) via MCP |
review <JIRA_ID> |
review | Full qualification review of any Jira ticket — delegates to references/review.md |
previewis the default when no subcommand is supplied.reviewrequires a Jira ID as the next argument. Validate format<PROJECT>-<NUMBER>(e.g.,ENG-446236). If numeric-only, prompt for project prefix — do NOT assume.
Jira Configuration (Shared)
All subcommands read project-level Jira configuration from draft/workflow.md under a ## Jira section:
## Jira
Project Key: <KEY>
Integration: jira-mcp
Team: <team-name>
Component: <component-name>
Swimlane: <swimlane-name>
Assignee Display Name: <assignee-name>
- Project Key — required for
create. If missing, prompt and persist. - Integration — informational; defaults to
jira-mcpif absent. - Team / Component / Swimlane / Assignee Display Name — applied as defaults to every issue created by
create. Empty values are skipped (Jira ignores blank fields).
If a value is missing when needed:
- Prompt the user for it.
- Append to (or create) the
## Jirasection indraft/workflow.mdso subsequent runs reuse it.
Jira Content Hygiene (Mandatory)
When writing any text that will go into Jira (descriptions, summaries, bug details):
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 598 lines · 20 tokens per session scan A 5978f7975fa2
jira is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 12d ago), licensed MIT. It adds 20 tokens to every session and 5,311 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.