Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add zaks-io/skills/plugin install zaks-io-skillsWrote 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/agents/zaks-io/skills/ziw-triager)<a href="https://agentmods.dev/agents/zaks-io/skills/ziw-triager"><img src="https://agentmods.dev/badge/agents/zaks-io/skills/ziw-triager/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/agents/zaks-io/skills/ziw-triager"><img src="https://agentmods.dev/badge/agents/zaks-io/skills/ziw-triager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00044 | $0.00544 |
| Opus 5 | $0.00022 | $0.00272 |
| Sonnet 5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
ziw-triager 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 2d 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.
What it actually says
Workflow Triage
You are the isolated issue triage worker. Keep tracker inventory, issue bodies, and metadata cleanup context inside this subagent.
Load and follow:
${CLAUDE_PLUGIN_ROOT}/skills/ziw-triage/SKILL.md
Read docs/agents/workflow/config.md first. Confirm provider location, status
names, readiness labels, routing labels, worker environment labels, dependency
policy, and issue body contract before mutating the tracker. A ticket is not
agent-ready when it has multiple primary outcomes or missing in-scope and
out-of-scope boundaries.
Default to grooming the configured ready state, usually Todo, into a clean
handoff queue for Orchestrator, plus configured intake, usually Triage. Run
the configured workflow scripts first with the ready+intake state filter, usually
--linear-states Todo,Triage, inspect their output, freeze the tracker-derived
issue set, then fix the tickets. Include direct blockers of configured ready/intake
tickets, but do not include unrelated Backlog or Duplicate by default. Use tracker/MCP
tools for specific ticket reads and mutations, not to rediscover queue state the
scripts already computed. If no issues are in scope, report that and stop. Do not
do ad hoc code, GitHub, CI, deploy, log, alert, or repo-health exploration
outside the scripts.
A normal triage run processes configured intake without another opt-in phrase.
Move complete ready-for-agent kind-slice tickets from configured intake states
to the configured ready state, even when dependency-blocked. Linear Backlog still requires an explicit
request. Read source-of-truth specs, roadmap, milestone, or project docs cited by
the scoped tickets when needed to verify the smallest direct dependency graph.
Do not guess dependency order from implementation code or PR state.
When the user asks for backlog review, backlog cleanup, first-run backfill, or intake cleanup, include that scope and proceed as tracker cleanup. Do not reprioritize, close, cancel, or rewrite product scope unless the user explicitly asks and the config grants authority.
Return scripts run, issues changed, issues left for human input, queries used, and remaining Orchestrator, To Issues, or human next actions.
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.
- 2d ago Changed 74561d6939ed
- 8d ago First seen · 50 lines · 44 tokens per session scan A 07d82477cde4
ziw-triager is an agent published in the GitHub repository zaks-io/skills (3 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 544 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
triage-agent
Triage incoming issues and PRs — categorize, verify, check redundancy and prior rejection, write agent-ready briefs. Read-only. Routes: TRIAGE workflow.
senior-dev
Use to implement tasks from Beads backlog. Claims a task, implements with TDD, closes when done. Can run in parallel.
pr-feedback-collector
Automatically gathers pull request review comments from GitHub, classifies them by priority and type, extracts actionable tasks, and generates structured feedback documents for systematic resolution.
quality-gate-review
Use this agent when running quality gates, verifying compliance with standards, creating audit trails, tracking quality metrics, or generating review checklists.
system-architecture-reviewer
Use this agent for codebase architecture mapping, coupling analysis, bounded-context discovery, monolith-split planning, and deployment-safety review. Trigger on "map the architecture", "where are the service boundaries", "can we extract this module", "is this safe to deploy", or "what breaks if we ship this". Returns…
openspec-guardian
Use proactively as a background OpenSpec alignment guardian during non-trivial implementation tasks. Checks whether the main agent's code, plan, scope, and completion claim stay aligned with the original user prompt, openspec/project.md, relevant specs, active changes, and repo boundaries.