A script-guided process for cleaning up a project's issue tracker backlog. It checks whether tickets have the labels, status, dependencies, estimates, and details needed for an agent to implement them.

Use it to prepare implementation tickets, identify blockers, fix tracker metadata, and separate work that needs human decisions.

It turns vague or stale tickets into ready work or clearly marked follow-up, so agents do not need to re-triage the backlog.

ziw-triage — Skill for Claude Code and Codex by zaks-io/skills

Install

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.

Any agent

npx skills add zaks-io/skills --skill ziw-triage

Clone the repo

git clone --depth 1 https://github.com/zaks-io/skills

Made for: Claude Code, Codex.

Or install zaks-io-skills, the plugin that ships this one along with the rest of its 10 skills, 3 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zaks-io/skills/ziw-triage/github.svg)](https://agentmods.dev/skills/zaks-io/skills/ziw-triage)

Your own site

<a href="https://agentmods.dev/skills/zaks-io/skills/ziw-triage"><img src="https://agentmods.dev/badge/skills/zaks-io/skills/ziw-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zaks-io/skills/ziw-triage"><img src="https://agentmods.dev/badge/skills/zaks-io/skills/ziw-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 645 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00046	$0.00645
Opus 5.5	$0.00018	$0.00258
Sonnet 5.5	$0.00009	$0.00129
Haiku 4.5	$0.00005	$0.00064

Measured yesterday against content hash 4393b7a31645, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ziw-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 yesterday.

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.

skills/ziw-triage/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Triage

Leave the queue with only ready tickets in the ready state, and a named next owner for every other ticket. Terms and labels follow the workflow contract.

Inputs

The repo config and a scope. By default the scope is the intake and ready states; other states, such as Backlog, only when the user names them.

Steps

Run the snapshot for the scope:

node <skill-dir>/../ziw-orchestrate/scripts/tick-snapshot.mjs --repo <owner/repo> \
  --linear-team <team> --linear-route-label <route label> \
  --linear-states <scope states> > /tmp/triage-snapshot.json

If the snapshot fails or skips the tracker, list the scope once with tracker tools instead.

Give each ticket one outcome:
- Ready: the body and labels are complete. Move it to the ready state with ready-for-agent, even when it is blocked.
- To Issues: too big, vague, a container, or missing body sections. Add needs-info with the exact gap.
- Human: needs a human decision. Add ready-for-human and the question.
- Leave: in progress, has a PR, a duplicate, or parked outside the requested scope. Orchestrate owns active work; note anything stale for it.
For To Issues and Human, also remove ready-for-agent and move the ticket to the intake state.
Fix metadata the evidence makes obvious: a missing route, kind, or risk label, and blockers stated in a ticket or its spec. Make one combined update per ticket.
Rerun the snapshot, then the dependency check, and report its cycles and blockers with the fix or owner for each:
```
node <skill-dir>/../ziw-orchestrate/scripts/linear-dag-start.mjs /tmp/triage-snapshot.json
```
If you listed tickets with tracker tools, list them again and pass them as a JSON array instead.

Rules

Read only the tracker, config, cited specs, and script output. Never read code, PRs, or CI to decide scope or order.
Change only tickets in the requested scope.
Don't close, cancel, reprioritize, or rewrite scope unless asked.
If the tracker rate-limits you, stop all tracker calls and report the changes still pending.

Read the full file on GitHub · 69 lines

Files

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.

agents/openai.yaml 275 B

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.

yesterday Changed · -160 lines · -18 tokens per session 4393b7a31645
3d ago Changed · -198 lines 08b4b8ef6b16
12d ago Changed · +43 lines 2f3153ee1ca0
20d ago Changed · +15 lines 7bbaf88941d7
25d ago Changed · +3 lines e71151f97cd6
29d ago Changed · -64 lines f8e0e30929bc
1mo ago Changed · +24 lines c5b6c0d9a761
2mo ago First seen · 406 lines · 64 tokens per session scan A 6d985ea77ea7

Subscribe to this mod's changes

ziw-triage is a skill published in the GitHub repository zaks-io/skills (3 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 645 once invoked, about $0.0002 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 2026-08-31.

Code review Project management agent-workflows ai-agents claude codex issue-triage

jira-issue-create

Create one or more Jira issues through acli from user-approved drafts using heading-based Context, Acceptance criteria, and Engineering notes sections. Use only when explicitly invoked to create Jira issues; use jira-issue-refine when requirements still need refinement.

yarlson/yarstack · 53 tokens

roadmap-task-deliver

Deliver the first eligible unfinished roadmap task through implementation, review, green CI, PR merge, and a task-status update. Use for autonomous delivery from local roadmap and task files. Files can be outside the code repository or outside Git.

yarlson/yarstack · 52 tokens

jira-issue-deliver

Autonomously deliver one Jira issue from intake to a ready GitHub pull request. Use only when the user authorizes implementation, commits, pushes, PR state changes, CI remediation, and resolution of requested automated review feedback.

yarlson/yarstack · 51 tokens

plan-deliver

Autonomously deliver an approved implementation plan to a ready GitHub pull request. Use when the user supplies a plan in the conversation or a file and authorizes implementation, commits, pushes, PR state changes, CI remediation, and resolution of requested automated review feedback; use jira-issue-deliver when the…

yarlson/yarstack · 71 tokens

jira-issue-refine

Refine one draft or existing Jira issue into a clear, evidence-backed, bounded delivery contract without implementing it. Use when creating or revising an issue before engineering handoff, especially when behavior, repository ownership, acceptance evidence, dependencies, risk, environment needs, or scope remain…

yarlson/yarstack · 63 tokens

ai-maintainer-copilot

Use when maintaining open-source projects with AI assistance: issue triage, pull request review, release notes, maintainer automation, Codex for OSS application evidence, and privacy or safety guardrails for AI-assisted workflows.

yuxiaoji30-lang/ai-maintainer-copilot-skill · 50 tokens