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 mhawthorne/gza --skill gza-task-draftgit clone --depth 1 https://github.com/mhawthorne/gzaWrote 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/mhawthorne/gza/gza-task-draft)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-task-draft"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-task-draft/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/mhawthorne/gza/gza-task-draft"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-task-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
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 →
- low Excessive Agency · line 38 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00021 | $0.01197 |
| Opus 5.5 | $0.00008 | $0.00479 |
| Sonnet 5.5 | $0.00004 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
gza-task-draft 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Gza Task
Guide the user through a deliberate task creation process: clarify scope, surface risks, draft a prompt, get approval, then run uv run gza add.
Step 1: Read conventions
Read /workspace/AGENTS.md — specifically the "Creating Tasks from Conversations" section — to understand task types, flags, and prompt conventions.
Step 2: Assess description detail
Evaluate how detailed the user's description already is:
If vague or missing key context (objective unclear, scope undefined, approach unspecified): ask clarifying questions using AskUserQuestion (max 4 questions per call, 2–4 options each).
Focus on what matters most:
- What is the core objective / what problem does this solve?
- What type of work is this? (explore/plan/implement/review/task)
- Are there constraints, dependencies, or related tasks?
- What does "done" look like?
If already detailed (clear objective, known scope, specific requirements): skip to Step 3 directly.
Step 3: Draft the prompt + surface concerns
Draft a task prompt that:
- States the objective clearly and specifically
- References file paths, modules, or components when known
- Sets scope (what's in and out)
- Includes acceptance criteria for implement tasks
- Includes non-goals for implement tasks so the agent does not expand scope silently
- Names required tests or concrete failure modes to cover when known
- Calls out docs/help/config updates when operator-facing behavior changes
- Is appropriately sized (one task, one objective)
For implement tasks, push toward a prompt shape like:
- Objective
- Acceptance criteria
- Non-goals
- Relevant files/modules or affected subsystem
- Required tests
- Required docs/help/config updates, if applicable
If too many of those fields are unknown, ambiguous, or cross-cutting, recommend splitting the work or creating a plan task first rather than drafting a vague implement prompt.
Also identify and surface:
- Risks: What could go wrong or cause rework?
- Ambiguities: Unclear requirements that could derail the task
- Alternatives: Different approaches worth considering
- Sequencing: Should this be split (plan first, then implement)? Does it need
--depends-onor--based-on?
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 · 116 lines · 21 tokens per session scan A 8d3a5c8ef4b6
gza-task-draft is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed 6d ago), licensed MIT. It adds 21 tokens to every session and 1,197 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-triage
Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.
tencent-meeting-mcp
A Tencent Meeting assistant for scheduling meetings and working with participants, recordings, transcripts, and AI-generated meeting notes.
flow-next-flow
Use first in a Flow-Next repo for a spec id, change, bug, issue, slow code or metric, cleanup, design fork, dump to explain, repeated mistake, prompt change, what could break, what next. No quick asks.
flow-next-plan
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.