workflow-issue-triage

workflow-issue-triage is a skill for Claude Code from saemihemma/lead-producer-oss. It costs 48 tokens per session (531 once invoked), scanned A, original, MIT.

A bug handoff workflow that turns investigation findings into a durable Markdown document. The document records the problem, reproduction steps, likely cause, test-driven development fix plan, acceptance criteria, and open questions.

In plain words
What is it for?
It helps prepare a clear bug report after investigation, including how to reproduce the issue, what caused it, how to test the fix, and who should own the next steps.
Why use it?
It keeps debugging evidence and follow-up work together when investigation and implementation happen at different times or involve different people.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps prepare a clear bug report after investigation, including how to reproduce the issue, what caused it, how to test the fix, and who should own the next steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saemihemma/lead-producer-oss/workflow-issue-triage
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 saemihemma/lead-producer-oss --skill workflow-issue-triage
Clone the repo
git clone --depth 1 https://github.com/saemihemma/lead-producer-oss

Made for: Claude Code.

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.

agentmods badge for workflow-issue-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/workflow-issue-triage/github.svg)](https://agentmods.dev/skills/saemihemma/lead-producer-oss/workflow-issue-triage)
Your own site
<a href="https://agentmods.dev/skills/saemihemma/lead-producer-oss/workflow-issue-triage"><img src="https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/workflow-issue-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.

agentmods 80×15 button for workflow-issue-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/saemihemma/lead-producer-oss/workflow-issue-triage"><img src="https://agentmods.dev/badge/skills/saemihemma/lead-producer-oss/workflow-issue-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 531 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.00531
Opus 5 $0.00024 $0.00266
Sonnet 5 $0.00010 $0.00106
Haiku 4.5 $0.00005 $0.00053

Measured 12d ago against content hash f90b39153a44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

workflow-issue-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 12d 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.

.claude/skills/workflow-issue-triage/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Triage Workflow

Purpose

Packaging and handoff layer for debugging work. Turns findings from prior investigation into a durable local artifact with clear next steps and ownership.

Use When

  • Investigation findings need a durable local artifact
  • Clean handoff is needed after workflow-systematic-debugging, Dev Team, QA, or manual investigation
  • Reproduction notes, root-cause summary, acceptance criteria, and fix slices should live in one place
  • Task spans investigation now and implementation later

Do NOT Use When

  • Root cause is still unknown and the next step is investigation (use workflow-systematic-debugging)
  • Issue is already understood and user wants direct implementation
  • Task is feature request, not bug

Default Artifact

Persist to _artifacts/triage-<slug>.md:

  • Problem
  • Reproduction
  • Root Cause Summary
  • TDD Fix Plan
  • Acceptance Criteria
  • Open Questions / Unknowns

Packaging Workflow

  1. Capture the best investigation evidence available.
  2. Record tightest reliable reproduction.
  3. State confirmed root cause plainly; if still unconfirmed, label the current best hypothesis and confidence.
  4. Package next fix steps as small TDD-oriented slices.
  5. Assign likely follow-up owner.
  6. Record what remains unknown.

TDD Fix Plan

Each slice should answer:

  • What failing behavior to capture first?
  • Smallest implementation change to make test pass?
  • Cleanup or refactor that waits until slice is green?

Anti-Patterns

  • Behavior-level explanations, not file-by-file edit lists.
  • Name root cause plainly; rank multiple candidates by confidence.
  • Make acceptance criteria observable and testable.

Output Discipline

  • Follow the Default Output structure as both minimum and maximum. Do not add extra sections.
  • Keep findings concise: 2-5 points per section.

Anti-Drift Rules

  • This workflow packages investigation results. It does not perform root-cause debugging.
  • If _artifacts/ directory does not exist, ask the user where to save artifacts.
  • If the next best step is still root-cause investigation, route to workflow-systematic-debugging instead of guessing.
  • Name root cause plainly. Do not hide uncertainty behind confident language.
  • Make acceptance criteria observable and testable, not vague.

Read the full file on GitHub · 59 lines

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.

  1. 12d ago First seen · 59 lines · 48 tokens per session scan A f90b39153a44

Subscribe to this mod's changes

workflow-issue-triage is a skill published in the GitHub repository saemihemma/lead-producer-oss (2 stars, last pushed 8d ago), licensed MIT. It adds 48 tokens to every session and 531 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.