work-issue

work-issue is a skill for Claude Code, Codex from shwilliamson/automatasaurus. It costs 33 tokens per session (4,772 once invoked), scanned B, original, MIT.

The implementation workflow for handling one GitHub issue, a tracked development task or bug report. It coordinates setup, dependencies, design, coding, reviews, testing, and reporting.

In plain words
What is it for?
Use it to implement a single issue, coordinate developers and reviewers, handle requested changes, and preserve an audit trail.
Why use it?
It gives issue work a repeatable process and records whether the task was completed, blocked, or escalated.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions subagents.

Good fit Use it to implement a single issue, coordinate developers and reviewers, handle requested changes, and preserve an audit trail.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shwilliamson/automatasaurus/work-issue
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 shwilliamson/automatasaurus --skill work-issue
Clone the repo
git clone --depth 1 https://github.com/shwilliamson/automatasaurus

Made for: Claude Code, Codex.

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 work-issue

README.md
[![agentmods](https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/work-issue/github.svg)](https://agentmods.dev/skills/shwilliamson/automatasaurus/work-issue)
Your own site
<a href="https://agentmods.dev/skills/shwilliamson/automatasaurus/work-issue"><img src="https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/work-issue/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 work-issue

Your own site · 80×15
<a href="https://agentmods.dev/skills/shwilliamson/automatasaurus/work-issue"><img src="https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/work-issue.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,772 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00033 $0.04772
Opus 5.5 $0.00013 $0.01909
Sonnet 5.5 $0.00007 $0.00954
Haiku 4.5 $0.00003 $0.00477

Measured 2mo ago against content hash 587737dd1cd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

work-issue scanned grade B with 1 finding 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 2mo 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat .claude/settings.json | grep -A3 'teamPrefer'
template/skills/work-issue/SKILL.md · 693 lines

How it starts

The opening of the file, as written. The whole thing — 693 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work Issue Skill

This skill contains the implementation logic for working on a single GitHub issue. It is loaded by:

  • /auto-work-issue {n} command (direct invocation)
  • /auto-work-all subagents (spawned for context isolation)

Input

This skill expects an ISSUE_NUMBER to be provided by the caller.

Workflow

1. PRE-FLIGHT CHECK → Verify commands.md exists and is complete
2. SETUP ORCHESTRATION FOLDER
3. GET ISSUE DETAILS
4. CHECK DEPENDENCIES → If blocked, report and stop
4.5. CHOOSE COORDINATION MODE → Teams vs subagents for each step
5. GET DESIGN SPECS (if UI) → Invoke designer agent with briefing
6. IMPLEMENT → Invoke developer agent (or team) with briefing
7. COORDINATE REVIEWS → Architect, Designer (if UI), Tester (subagents or team)
8. HANDLE CHANGE REQUESTS → Loop until all approved
9. COMMIT ORCHESTRATION FILES → Preserve audit trail in branch
10. REPORT RESULT → Success, Blocked, or Escalated

Step 1: Pre-flight Check

Before starting work, verify the project is set up for E2E testing.

Check commands.md Exists and Is Complete

# Check if commands.md exists
if [ ! -f .claude/commands.md ]; then
  echo "ERROR: .claude/commands.md does not exist"
fi

# Read and check for required commands
cat .claude/commands.md

Required commands that must be documented:

  • Development server command (how to run the app)
  • Development server URL (where the app runs)
  • Test command (how to run tests)

If commands.md Is Missing or Incomplete

STOP and report to the user:

PRE-FLIGHT FAILED: commands.md is incomplete

Before I can work on issues, .claude/commands.md must document:
- How to start the development server
- The URL where the app runs
- How to run tests

Please update .claude/commands.md with these commands, or I won't be able to verify the implementation works.

Do NOT proceed until commands.md is complete. The Tester agent will need this to run E2E verification, and skipping E2E verification is unacceptable.

Read the full file on GitHub · 693 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. 2mo ago First seen · 693 lines · 33 tokens per session scan B 587737dd1cd0

Subscribe to this mod's changes

work-issue is a skill published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 8mo ago), licensed MIT. It adds 33 tokens to every session and 4,772 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

work-issue compared with skills from other repositories

work-issue next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
work-issueshwilliamson/automatasaurusSkill58mo agoMITB33Claude Code, Codex
merge-batchdiegosouzapw/OmniRouteSkill83k6d agoMITA46Claude Code
prowler-commitprowler-cloud/prowlerSkill15kyesterdayApache-2.0A44Claude Code, Codex
gh-auth-isolationgithub/gh-awSkill5.6kyesterdayMITA20Claude Code, Codex
github-skillzeenie-ai/OpenCompanySkill1.1kyesterdayMITA51Claude Code
comet-githubrpamis/cometSkill3.3kyesterdayMITA72Claude Code, Codex
release-helperSahir619/fable-methodSkill2.3k1mo agoMITA43Claude Code