torque:check

A diagnostic check for installations that use GSD and Superpowers, two development-workflow systems. It checks whether they are present, reports versions, and looks for missing core skills or configuration conflicts.

In plain words
What is it for?
Use it when checking a Torque project, verifying GSD and Superpowers installation, investigating missing skills, or looking for common setup problems.
Why use it?
It helps explain why the workflow is not working by finding absent components and mismatched or conflicting setup before deeper troubleshooting.

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/mattjaikaran/torque/check
Any agent
npx skills add mattjaikaran/torque --skill check
Clone the repo
git clone --depth 1 https://github.com/mattjaikaran/torque

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00034 $0.00830
Opus 5 $0.00017 $0.00415
Sonnet 5 $0.00007 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 3d ago against content hash fb30d80b13cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

torque:check scanned grade C with 2 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 3d 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/get-shit-done/VERSION 2>/dev/null || echo "GSD_VERSION=unknown"

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls ~/.claude/skills/gsd-* 2>/dev/null | head -5
skills/check/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Torque Health Check

Verify that GSD and Superpowers are installed correctly and the current project has no configuration conflicts.

Procedure

Step 1: Check GSD installation

# Check for GSD tools
ls ~/.claude/get-shit-done/bin/gsd-tools.cjs 2>/dev/null && echo "GSD_INSTALLED=true" || echo "GSD_INSTALLED=false"

# Get GSD version
cat ~/.claude/get-shit-done/VERSION 2>/dev/null || echo "GSD_VERSION=unknown"

# Check GSD skills are registered
ls ~/.claude/skills/gsd-* 2>/dev/null | head -5

Step 2: Check Superpowers installation

# Check for core SP skills (required)
for skill in systematic-debugging test-driven-development brainstorming writing-plans subagent-driven-development requesting-code-review verification-before-completion finishing-a-development-branch receiving-code-review; do
  if ls ~/.claude/skills/$skill/SKILL.md 2>/dev/null > /dev/null; then
    echo "  ✓ $skill"
  else
    echo "  ✗ $skill (MISSING)"
  fi
done

# Check for extended SP skills (optional but recommended)
echo ""
echo "Extended skills:"
for skill in grill-me improve-codebase-architecture write-a-prd prd-to-issues changelog-generator webapp-testing playwright-skill ci-cd monitoring-observability; do
  if ls ~/.claude/skills/$skill/SKILL.md 2>/dev/null > /dev/null; then
    echo "  ✓ $skill"
  else
    echo "  ○ $skill (optional, not installed)"
  fi
done

Step 3: Check Torque installation

# Verify this skill is properly installed
ls ~/.claude/skills/torque/SKILL.md 2>/dev/null && echo "TORQUE_INSTALLED=true" || echo "TORQUE_INSTALLED=false"

Step 4: Project-level checks

Run these checks in the current working directory:

  1. Mixed plan locations: Flag if both .planning/ AND docs/plans/ exist
  2. Orphaned .planning/: Flag if .planning/ exists but has no PROJECT.md (manually created)
  3. Stale state: Flag if .planning/STATE.md references a phase that doesn't have a directory
  4. Missing reviews: Flag if any phase has VERIFICATION.md but no code review was done (check git log for review commits)

Read the full file on GitHub · 103 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. 3d ago First seen · 103 lines · 34 tokens per session scan C fb30d80b13cc

Subscribe to this mod's changes

torque:check is a skill published in the GitHub repository mattjaikaran/torque (6 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 830 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). 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