Agent skill

Gsd Plan Checker

by allgpt-co in allgpt-co/QuickVoice

Validates plan quality by checking task completeness, dependency correctness, and scope sanity.

MITAuto-check passedTesting & QA

Install Gsd Plan Checker

skills CLI
$ npx skills add allgpt-co/QuickVoice --skill gsd-plan-checker -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install allgpt-co/QuickVoice gsd-plan-checker --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/allgpt-co/QuickVoice.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/gsd/agents/plan-checker .claude/skills/gsd-plan-checker && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gsd-plan-checker
GitHub stars
488
Token cost
~2.5k tokens
SKILL.md length
645 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Validates plan quality by checking task completeness, dependency correctness, and scope sanity.

  • Works in 12 steps: Task Completeness → Dependency Correctness → File Ownership → …
  • Testing & QA work in your project
  • SKILL.md covers When to Use, Core Responsibilities, Philosophy and Validation Dimensions, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gsd Plan Checker is an agent skill from allgpt-co/QuickVoice. Validates plan quality by checking task completeness, dependency correctness, and scope sanity. Spawned by /gsd:plan-phase orchestrator.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA. The repository describes itself as: Open-source, self-hostable platform for building and operating AI phone agents. The licence is MIT.

When your agent uses it

  • Testing & QA work in your project

Example prompts

  • “Use the gsd-plan-checker skill to validate plan quality by checking task completeness, dependency correctness, and scope sanity”
  • “/gsd-plan-checker”

Workflow steps

12 steps, taken from the step headings in SKILL.md.

  1. Task Completeness
  2. Dependency Correctness
  3. File Ownership
  4. Scope Sanity
  5. Must-Haves Derivation
  6. Load Plans
  7. Parse Frontmatter
  8. Validate Task Completeness
  9. Check Dependency Correctness
  10. Check File Ownership
  11. Validate Must-Haves
  12. Validate Scope Sanity

What it can do on your machine

Read from SKILL.md and the folder at commit 89fa8ff. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gsd Plan Checker loads about 2.5k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 645 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from allgpt-co/QuickVoice at commit 89fa8ff, republished under its MIT licence (© allgpt-co). 645 words, ~2,468 tokens.

Download SKILL.mdSave it as .claude/skills/gsd-plan-checker/SKILL.md (or your agent's skills folder).
name
gsd-plan-checker
description
Validates plan quality by checking task completeness, dependency correctness, and scope sanity. Spawned by /gsd:plan-phase orchestrator.
version
1.0.0
author
GSD Project
tags
plan-validation, quality-assurance, dependency-analysis
triggers
verify plans, check plan quality, validate dependencies
tools
Read, Bash, Grep, Glob

GSD Plan Checker

Validates plan quality by checking task completeness, dependency correctness, and scope sanity.

When to Use

Use this agent when:

  • Plans have been created by gsd-planner and need validation
  • You are spawned by /gsd:plan-phase orchestrator during verification loop
  • Plans need to pass quality checks before execution

Core Responsibilities

  1. Validate task completeness - Every task must have all required elements
  2. Check dependency correctness - Verify depends_on arrays are accurate
  3. Verify file ownership - Check for conflicts between parallel plans
  4. Validate scope sanity - Ensure plans are appropriately sized
  5. Check must_haves derivation - Verify goal-backward methodology was used
  6. Identify issues - Categorize problems by severity
  7. Return structured issues - Provide actionable feedback for revision

Philosophy

Quality Gate

Plans that pass all checks are ready for execution. Plans with issues need revision.

Anti-pattern:

  • Don't approve plans with obvious gaps
  • Be specific about what needs fixing
The Checker's Role

You are a quality gate, not a blocker. Your job is to ensure plans are executable and well-structured.

Validation Dimensions

1. Task Completeness

Every task must have these required elements:

Required fields:

  • <name> - Task name (action-oriented)
  • <files> - Exact file paths created/modified
  • <action> - Specific implementation instructions
  • <verify> - How to prove task is complete
  • <done> - Acceptance criteria (measurable state)

Common issues:

  • Missing <verify> element
  • Vague <action> (not specific enough)
  • Vague <done> (not measurable)
  • Missing <files> for auto tasks
2. Dependency Correctness

Validate depends_on arrays:

  • All plan IDs in depends_on must exist
  • No circular dependencies (A depends on B, B depends on A)
  • Wave assignments are correct (Wave N depends only on Wave N-1 or earlier)

Common issues:

  • Invalid plan IDs in depends_on
  • Self-dependencies (plan depends on itself)
  • Cyclic dependencies
3. File Ownership

Check for conflicts:

  • Files appear in multiple files_modified arrays
  • Wave 1 plans have no overlapping files

Common issues:

  • Same file in parallel Wave 1 plans
4. Scope Sanity

Check plan sizing:

  • Each plan has 2-3 tasks maximum
  • No plan has >5 files modified
  • No plan has checkpoint + implementation work in same plan

Common issues:

  • Plan with 4+ tasks (too large)
  • Plan with >5 files modified (too large)
  • Checkpoint + implementation in same plan (should be separate)
5. Must-Haves Derivation

Verify goal-backward methodology:

  • must_haves section exists in frontmatter
  • Contains truths, artifacts, key_links (not just tasks)

Common issues:

  • Missing must_haves entirely
  • must_haves contain tasks instead of outcomes
  • No key_links defined
  • No artifacts defined
Show full SKILL.md (258 more words)Show less

Process

Step 1: Load Plans

Read all PLAN.md files in phase directory:

bash
PHASE_DIR=$(find .planning/phases -name "${PHASE}-*" -type d | head -1)

for plan in "$PHASE_DIR"/*-PLAN.md; do
  cat "$plan"
done
Step 2: Parse Frontmatter

Extract from each PLAN.md:

  • phase, plan, type, wave, depends_on, files_modified, autonomous, must_haves
Step 3: Validate Task Completeness

For each task in each plan:

Check auto tasks:

bash
# Extract tasks
grep -A 20 '<task type="auto"' "$plan_file"

for task in "$tasks"; do
  # Check for required elements
  has_name=$(echo "$task" | grep -q '<name>')
  has_files=$(echo "$task" | grep -q '<files>')
  has_action=$(echo "$task" | grep -q '<action>')
  has_verify=$(echo "$task" | grep -q '<verify>')
  has_done=$(echo "$task" | grep -q '<done>')

  if [ -z "$has_name" ] || [ -z "$has_files" ] || [ -z "$has_action" ] || [ -z "$has_verify" ] || [ -z "$has_done" ]; then
    echo "INCOMPLETE: $task"
  fi
done

Check checkpoint tasks:

bash
# Extract checkpoints
grep -A 20 '<task type="checkpoint' "$plan_file"

for task in "$tasks"; do
  has_what=$(echo "$task" | grep -q '<what-built>\|<decision>\|<action>')
  has_how=$(echo "$task" | grep -q '<how-to-verify>\|<options>\|<steps>')
  has_resume=$(echo "$task" | grep -q '<resume-signal>')

  if [ -z "$has_what" ] || [ -z "$has_how" ] || [ -z "$has_resume" ]; then
    echo "INCOMPLETE: $task"
  fi
done
Step 4: Check Dependency Correctness
bash
# Collect all plan IDs
for plan_file in "$PHASE_DIR"/*-PLAN.md; do
  plan_id=$(grep "^plan:" "$plan_file" | sed 's/plan: //')

  echo "$plan_id"
done > plan_ids

# Build dependency graph
for plan_id in $(cat plan_ids); do
  # Extract depends_on
  depends_on=$(grep "^depends_on:" "$PHASE_DIR"/*-PLAN.md | sed 's/depends_on: //; s/\[//g\]//g')

  echo "Plan $plan_id depends on: $depends_on"
done

# Validate
for plan_id in $(cat plan_ids); do
  # Check if dependencies exist
  for dep in $depends_on; do
    if ! grep -q "^$dep:" "$PHASE_DIR"/*-PLAN.md; then
      echo "MISSING: $plan_id depends on $dep (not found)"
      break
  fi
  done

  # Check for circular dependencies
  for plan_id in $(cat plan_ids); do
    if grep -q "^depends_on:.*$plan_id" "$PHASE_DIR"/*-PLAN.md; then
      echo "CIRCULAR: $plan_id depends on itself"
      break
  fi
  done
Step 5: Check File Ownership
bash
# Collect all files_modified arrays
for plan_file in "$PHASE_DIR"/*-PLAN.md; do
  grep -A 5 "^files_modified:" "$plan_file" | sed 's/.*\[\([^]]*\)\].*/\1/' | sort -u
done > all_files

# Check for duplicates
sort all_files | uniq -d > unique_files
for file in $(cat unique_files); do
  count=$(grep -c "$file" "$PHASE_DIR"/*-PLAN.md | wc -l)
  if [ "$count" -gt 1 ]; then
    echo "CONFLICT: $file appears in multiple plans"
  fi
done
Step 6: Validate Must-Haves
bash
# Check each plan for must_haves
for plan_file in "$PHASE_DIR"/*-PLAN.md; do
  # Extract must_haves section
  must_haves=$(sed -n '/^must_haves:/,/^---/p' "$plan_file" | sed '1,/^---/d')

  if [ -z "$must_haves" ]; then
    echo "MISSING: $plan has no must_haves"
  elif ! echo "$must_haves" | grep -q "truths:" > /dev/null; then
      echo "INVALID: must_haves missing truths section"
    elif ! echo "$must_haves" | grep -q "artifacts:" > /dev/null; then
      echo "INVALID: must_haves missing artifacts section"
    elif ! echo "$must_haves" | grep -q "key_links:" > /dev/null; then
      echo "INVALID: must_haves missing key_links section"
    else
      echo "VALID: must_haves has proper structure"
  fi
done
Step 7: Validate Scope Sanity
bash
# Check task counts
for plan_file in "$PHASE_DIR"/*-PLAN.md; do
  task_count=$(grep -c '<task' "$plan_file" | wc -l)

  if [ "$task_count" -gt 3 ]; then
    echo "SCOPE WARNING: $plan has $task_count tasks (too large)"
  elif [ "$task_count" -lt 2 ]; then
    echo "SCOPE WARNING: $plan has $task_count tasks (too small)"
  fi
done

# Check file modifications
for plan_file in "$PHASE_DIR"/*-PLAN.md; do
  file_count=$(grep -A 5 "^files_modified:" "$plan_file" | sed 's/.*\[\([^]]*\)\].*/\1/' | wc -w)

  if [ "$file_count" -gt 5 ]; then
    echo "SCOPE WARNING: $plan modifies $file_count files (too large)"
  fi
done

# Check for checkpoint + implementation in same plan
for plan_file in "$PHASE_DIR"/*-PLAN.md; do
  has_auto=$(grep -q 'autonomous: true' "$plan_file")
  has_checkpoint=$(grep -q 'type="checkpoint' "$plan_file")

  if [ -n "$has_auto" ] && [ -n "$has_checkpoint" ]; then
    echo "SCOPE WARNING: $plan has checkpoint but marked autonomous"
  fi
done
Step 8: Identify Issues

Categorize findings by severity:

Blocker issues (prevent plan approval):

  • Missing required task elements
  • Circular dependencies
  • Invalid plan IDs

Major issues (should be fixed before execution):

  • Vague task actions
  • Missing must_haves entirely
  • Scope issues (too large, multi-subsystem)

Minor issues (can be addressed during execution):

  • Minor scope concerns
  • Informational notes needed
Step 9: Return Structured Issues

Format issues with severity and actionable feedback:

markdown
## ISSUES FOUND

**Blockers:**
- [Issue description]

**Major:**
- [Issue description]

**Minor:**
- [Issue description]

**Informational:**
- [Issue description]

Output

Create VERIFICATION-CHECKER.md

Write to .planning/phases/{phase_dir}/{phase}-VERIFICATION-CHECKER.md

Critical Rules

  • Be specific and actionable - Don't say "fix tasks", say "Add <verify> element to Task 2"
  • Categorize by severity - Separate blockers from minor issues
  • Focus on fixable issues - Prioritize things that can be addressed
  • Provide context - Include plan ID and specific line numbers
  • Don't block unnecessarily - Only mark as blocker if it truly prevents execution

Success Criteria

  • All plans loaded and parsed
  • Task completeness validated for all tasks
  • Dependency correctness verified (no cycles, waves accurate)
  • File ownership checked (no conflicts)
  • Must-haves validated (proper structure with truths/artifacts/links)
  • Scope sanity checked (appropriate sizing, no checkpoint+implementation)
  • Issues identified and categorized by severity
  • Structured issues report created
  • VERIFICATION-CHECKER.md written
  • @skills/gsd/agents/planner - Agent that created the plans being validated
  • @skills/gsd/agents/executor - Agent that will execute the plans

© allgpt-co, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/gsd/agents/plan-checker of allgpt-co/QuickVoice.

Open the folder on GitHubat commit 89fa8ff

Compare with similar skills

Gsd Plan Checker next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gsd Plan Checker compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gsd Plan Checker this skillallgpt-co/QuickVoice488—~2.5kAutomated safety check: PassMIT
Web Application Testinganthropics/skills180k51 repos~966Automated safety check: PassApache-2.0
Diagnosing Bugsfossasia/eventyay-interpretation1.6k32 repos~2.1kAutomated safety check: PassApache-2.0
TDDpietheinstrengholt/rssmonster56430 repos~906Automated safety check: PassMIT
TDD WorkflowhellangleZ/burn-in-cceverywhere-ralph11211 repos~2.4kAutomated safety check: PassNone
TDDsanity-io/sanity6.4k20 repos~1kAutomated safety check: PassMIT

Similar skills

  • Web Application Testing

    anthropics/skills

    Official

    Tests local web applications with Python Playwright scripts, checking frontend behavior, capturing screenshots and reading browser console logs.

    180k GitHub starsUsed in 51 repos~966 tokens
    Testing & QAAuto-check passed
  • Diagnosing Bugs

    fossasia/eventyay-interpretation

    Diagnosis loop for hard bugs and performance regressions. An agent skill from fossasia/eventyay-interpretation.

    1.6k GitHub starsUsed in 32 repos~2.1k tokens
    Testing & QAAuto-check passed
  • TDD

    pietheinstrengholt/rssmonster

    Test-driven development. An agent skill from pietheinstrengholt/rssmonster.

    564 GitHub starsUsed in 30 repos~906 tokens
    Testing & QAAuto-check passed
  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed
  • TDD

    sanity-io/sanity

    Official

    Test-driven development with red-green-refactor loop. An agent skill from sanity-io/sanity.

    6.4k GitHub starsUsed in 20 repos~1k tokens
    Testing & QAAuto-check passed
  • Context Driven Development

    Ibrahim-3d/orchestrator-supaconductor

    A skill your agent uses when working with Conductor's context-driven development methodology, managing project context artifacts, or understanding the relationship between product.md, tech-stack.md…

    381 GitHub starsUsed in 9 repos~2.9k tokens
    Testing & QAAuto-check passed

More from allgpt-co/QuickVoice

All 12 skills in this repo
  • Livekit Agents

    allgpt-co/QuickVoice

    Build voice AI agents with LiveKit Cloud and the Agents SDK.

    488 GitHub stars~3.3k tokensUpdated 5 days ago
    Auto-check: notes
  • Gsd

    allgpt-co/QuickVoice

    Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents

    488 GitHub stars~2k tokensUpdated 5 days ago
    Auto-check passed
  • Gsd Codebase Mapper

    allgpt-co/QuickVoice

    Explores codebase and writes structured analysis documents. An agent skill from allgpt-co/QuickVoice.

    488 GitHub stars~3.5k tokensUpdated 5 days ago
    Auto-check: notes
  • Gsd Integration Checker

    allgpt-co/QuickVoice

    Verifies that integrations work correctly by checking endpoints, responses, and data flow.

    488 GitHub stars~2.8k tokensUpdated 5 days ago
    Auto-check passed
  • Gsd Phase Researcher

    allgpt-co/QuickVoice

    Researches phase implementation for planning. An agent skill from allgpt-co/QuickVoice.

    488 GitHub stars~1.9k tokensUpdated 5 days ago
    Auto-check passed
  • Gsd Executor

    allgpt-co/QuickVoice

    Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management.

    488 GitHub stars~4.7k tokensUpdated 5 days ago
    Auto-check: warnings

Categories

Questions about Gsd Plan Checker

What does Gsd Plan Checker do?

Validates plan quality by checking task completeness, dependency correctness, and scope sanity. Gsd Plan Checker is an agent skill from allgpt-co/QuickVoice. Validates plan quality by checking task completeness, dependency correctness, and scope sanity.

When should I use Gsd Plan Checker?

Gsd Plan Checker fits situations like: testing & QA work in your project.

How do I install Gsd Plan Checker in Claude Code?

Run `npx skills add allgpt-co/QuickVoice --skill gsd-plan-checker -a claude-code`. Or copy the skill folder (.claude/skills/gsd/agents/plan-checker in allgpt-co/QuickVoice) into .claude/skills/gsd-plan-checker in your project. Claude Code loads it when a task matches its description.

How do I install Gsd Plan Checker in Codex?

Run `npx skills add allgpt-co/QuickVoice --skill gsd-plan-checker -a codex`. Or copy the skill folder (.claude/skills/gsd/agents/plan-checker in allgpt-co/QuickVoice) into .agents/skills/gsd-plan-checker in your project. Codex loads it when a task matches its description.

Can I use Gsd Plan Checker in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add allgpt-co/QuickVoice --skill gsd-plan-checker -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gsd-plan-checker, .gemini/skills/gsd-plan-checker, .github/skills/gsd-plan-checker and .opencode/skills/gsd-plan-checker in your project.

What does Gsd Plan Checker need to run?

SKILL.md names no scripts, command-line tools or credentials: Gsd Plan Checker is instructions for the agent only.

Does Gsd Plan Checker access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gsd Plan Checker safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gsd Plan Checker use?

Gsd Plan Checker is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gsd Plan Checker use?

About 2.5k tokens (SKILL.md is roughly 9.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gsd Plan Checker?

Skills that share tags, products or a category with Gsd Plan Checker: Web Application Testing (anthropics/skills, 180k stars), Diagnosing Bugs (fossasia/eventyay-interpretation, 1.6k stars), TDD (pietheinstrengholt/rssmonster, 564 stars) and TDD Workflow (hellangleZ/burn-in-cceverywhere-ralph, 112 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gsd Plan Checker?

allgpt-co (a GitHub organization) maintains it in allgpt-co/QuickVoice, which has 488 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 5, 2026.

Source: allgpt-co/QuickVoice on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.