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-triagegit 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-triage)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-task-triage"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-task-triage/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-triage"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-task-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Excessive Agency · line 42 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00061 | $0.03086 |
| Opus 5 | $0.00030 | $0.01543 |
| Sonnet 5 | $0.00012 | $0.00617 |
| Haiku 4.5 | $0.00006 | $0.00309 |
Grade A, and why
gza-task-triage 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 6d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gza Task Triage
Walk the gza incomplete "needs attention" list (or a single lineage) and decide, row by row, what the correct corrective action is. The output is a per-row classification plus a recommended gza command; this skill asks before doing anything — including drops.
This skill exists because the same conversation keeps recurring: gza watch runs the easy cases and leaves a small pile of merge units in gza incomplete that each need a judgment call. The slot below watch is the human triage step, and this skill systematizes it.
What this skill MUST NOT do
These guardrails are load-bearing. Do not relax them.
- Do not merge — never run
gza mergeorgit merge. - Do not retry or resume — never invoke
gza retryorgza resumeon your own. If a row looks like it warrants a resume, say so and stop; let the user run it. - Do not delete branches — never
git branch -Dor otherwise mutate refs. - Do not edit code — for review/improve churn that needs a real code fix, hand off to
/gza-task-fixrather than editing inline. - Ask per row — even for safe-looking drops, ask before executing.
If you find yourself wanting to do any of the above without explicit per-row confirmation, stop and report instead.
Process
Step 1: Resolve scope
The skill accepts an optional task ID.
- With ID: triage just that lineage. Resolve the merge-unit owner via
gza show <id>and look at the row that owns it. If the ID is not currently ingza incomplete, rungza show <id>and report the lifecycle anyway — the user may want to triage a lineage they expect to surface. - Without ID: ask how far back to look before gathering rows. Default to a recent sweep, not an all-time backlog walk.
For no-ID sweeps, start with AskUserQuestion and offer:
Last 1 hourLast 24 hours(default/recommended)Last 7 daysAll time
If the caller's intent is clearly recent (for example "what just failed?", "triage the latest watch output", "check today's attention rows"), proceed with Last 24 hours without asking a follow-up.
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.
- 6d ago Changed fe71362d7ab7
- 10d ago First seen · 174 lines · 61 tokens per session scan A dcd3f6ac641b
gza-task-triage is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed today), licensed MIT. It adds 61 tokens to every session and 3,086 once invoked, about $0.0003 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
issue
Register a bug, deferral, or known limitation as the next ISS-NNN in docs/registry/ISSUES.md with severity and an investigation path. Use when the user types /genesis:issue, says "log this bug/issue", "defer this", or when work uncovers a problem that will not be fixed in the current task in a GENESIS project.
triage
Triage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
ticket-grooming
Investigate and groom tickets by dispatching sub-agents for codebase research, history, root cause analysis, and risk assessment. Posts structured Triaging Notes as a comment. Default is short-form (TLDR, key findings, risks, estimation, approach) with full investigation collapsed. Use --full for the complete report.…
issue-lifecycle
Close resolved issues and surface next bugs after a fix is deployed.
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.