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-addgit 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-add)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-task-add"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-task-add/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-add"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-task-add.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 | $0.00021 | $0.01923 |
| Opus 5 | $0.00010 | $0.00962 |
| Sonnet 5 | $0.00004 | $0.00385 |
| Haiku 4.5 | $0.00002 | $0.00192 |
Grade A, and why
gza-task-add 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 9d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Gza Task
Create a well-scoped gza task with the appropriate type and configuration.
Process
Step 1: Understand gza task conventions
Read /workspace/AGENTS.md to understand:
- Task types (task, explore, plan, implement, review)
- Task format conventions
- When to use each type
Step 2: Gather task requirements
Ask the user what they want to accomplish. Use AskUserQuestion to gather:
-
What needs to be done? - The core objective or problem to solve
-
Task type - Present options:
task(default) - General purpose taskexplore- Research, investigation, or discovery workplan- Planning and design work that produces a specificationimplement- Code implementation based on clear requirementsreview- Code review or quality assessmentimprove- Address review feedback and/or unresolved task comments on an implementation. Runs from review findings, from unresolved comments, or from both; comments-only improve is supported when no usable review exists (useuv run gza improve <impl-id> --run)
-
Additional context (optional):
- Should this be tagged to relate it to other tasks? (--tag TAG, repeatable)
- Does this depend on another task? (--depends-on ID)
- For implement tasks: Should auto-create a review task? (--review)
- For chained work: Is this based on a previous task's output? (--based-on ID)
Step 3: Generate the task prompt
Create a clear, specific prompt that:
- States the objective clearly
- Includes relevant context (file paths, components, constraints)
- Is scoped appropriately for the task type
- For
plantasks: Explains what needs to be designed/explored - For
implementtasks: Specifies what to build, clear acceptance criteria, and any important constraints - For
reviewtasks: Identifies what to review and what to look for
For implement tasks, include at least these prompt elements when they are relevant:
- The exact behavior to change
- Non-goals or explicitly out-of-scope areas
- Relevant files, modules, or subsystems when known
- Required tests or failure modes to cover
- Required docs/help/config updates when operator-facing behavior changes
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.
- 9d ago First seen · 176 lines · 21 tokens per session scan A d2c5b6aee3b4
gza-task-add is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,923 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
aip-tracker
Track Airflow Improvement Proposal (AIP) implementation progress by comparing Confluence specs against codebase evidence. Use when asked to assess, report on, or compare AIP status.
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.
todo-for-ai-agent-runtime
Runtime integration skill for external agents connecting to Todo for AI over HTTP API Token / Agent Key, including auth, task lease, events, commit, and task logs.
tencent-meeting-mcp
A Tencent Meeting assistant for scheduling meetings and working with participants, recordings, transcripts, and AI-generated meeting notes.
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).