task-check

A quality-assurance command that checks whether code changes meet the requirements of a linked GitHub issue. QA means checking completed work against its stated requirements.

In plain words
What is it for?
Use it to verify an implementation against a GitHub issue, including required criteria and, optionally, stricter checks.
Why use it?
It helps catch missing acceptance criteria before a pull request is created. It can determine the issue from the branch name or accept an issue number.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/makigjuro/cloudstack-ai-plugins/task-check
Any agent
npx skills add makigjuro/cloudstack-ai-plugins --skill task-check
Clone the repo
git clone --depth 1 https://github.com/makigjuro/cloudstack-ai-plugins

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,667 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.01667
Opus 5 $0.00016 $0.00834
Sonnet 5 $0.00006 $0.00333
Haiku 4.5 $0.00003 $0.00167

Measured 2d ago against content hash 204f4d1eb82a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-check 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.

plugins/dev-workflow/skills/task-check/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Check (QA Verification)

Verify that the implementation on the current branch satisfies the requirements defined in the linked GitHub issue. This is a QA gate that ensures we built what was asked for.

Arguments

  • {issue} -- GitHub issue number (optional, extracted from branch name if not provided)
  • --strict -- Fail on any unmet criterion (default: fail only on "Must Have" criteria)

Configuration

Auto-detect the GitHub repository from git remote -v (extract owner and repo name). If cloudstack.json exists, it may contain a project.repository field as a fallback.

Process

Step 1: Identify the Issue

# Get current branch
BRANCH=$(git branch --show-current)

# Extract issue number from branch name (e.g., username/42-feature-name)
ISSUE=$(echo "$BRANCH" | grep -oE '/[0-9]+' | tr -d '/')

# If no issue in branch name and not provided as argument, fail
if [ -z "$ISSUE" ]; then
  echo "ERROR: Could not determine issue number. Provide as argument: /task-check 42"
  exit 1
fi

# Auto-detect repo from git remote
REPO_URL=$(git remote get-url origin)
OWNER=$(echo "$REPO_URL" | sed -E 's#.*[:/]([^/]+)/[^/]+(\.git)?$#\1#')
REPO=$(echo "$REPO_URL" | sed -E 's#.*[:/][^/]+/([^/]+?)(\.git)?$#\1#')

Step 2: Fetch Issue Details

Use MCP for structured issue data:

mcp__github-mcp-server__get_issue(owner: "${OWNER}", repo: "${REPO}", issue_number: $ISSUE)

This returns structured JSON with number, title, body, labels, state, and comments -- no CLI output parsing needed.

Step 3: Parse Acceptance Criteria

Extract acceptance criteria from the issue body. Look for:

  • Checkbox lists: - [ ] Criterion
  • "Acceptance Criteria" section
  • "Requirements" section
  • "Definition of Done" section
  • User stories with "so that" format

Categorize each criterion:

  • Must Have: Explicitly marked as required, or in "Acceptance Criteria"
  • Should Have: Listed but not critical
  • Nice to Have: Suggestions, future improvements mentioned

Read the full file on GitHub · 237 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. 2d ago First seen · 237 lines · 32 tokens per session scan A 204f4d1eb82a

Subscribe to this mod's changes

task-check is a skill published in the GitHub repository makigjuro/cloudstack-ai-plugins (1 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,667 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.

Related

Other skills, from other repositories