name: 17th-task-inspector description: | Use this skill for deep inspection of implementation against TASK.md using GPT-5.2-Codex. Provides thorough cross-model verification with detailed pass/fail analysis. Appropriate for: final verification, critical features, before claiming "done". Not appropriate for: quick checks (use task-validator), style review, test execution.

Task Inspector

Deep inspection of implementation against task specification using GPT-5.2 / GPT-5.2-Codex.

Usage

/task-inspector                    → gpt-5.2-codex, high (default)
/task-inspector high               → gpt-5.2-codex, high
/task-inspector xhigh              → gpt-5.2-codex, xhigh
/task-inspector high CODEX         → gpt-5.2-codex, high
/task-inspector xhigh CODEX        → gpt-5.2-codex, xhigh
/task-inspector high NONE          → gpt-5.2, high
/task-inspector xhigh NONE         → gpt-5.2, xhigh

Argument Parsing

Format: /task-inspector {effort} {model}

Argument	Values	Default
effort	`high`, `xhigh`	high
model	`CODEX`, `NONE`	CODEX

Model mapping:

CODEX → gpt-5.2-codex (optimized for coding)
NONE → gpt-5.2 (general model)

When to Use

After implementation complete, before claiming "done"
Critical features requiring high confidence
Cross-model verification needed

Implementation

Parse arguments and invoke the 17th-task-inspector subagent:

Task(
    description="Inspect implementation ({model}, {effort})",
    subagent_type="glm-worker:17th-task-inspector",
    prompt="""
Inspect implementation against {task_file_path}.

Configuration:
- Model: {model}  (gpt-5.2-codex or gpt-5.2)
- Effort: {effort}  (high or xhigh)
- Project root: {project_root}
""",
    run_in_background=true
)

Variables

Variable	Default	Description
effort	high	`high` or `xhigh`
model	gpt-5.2-codex	`gpt-5.2-codex` or `gpt-5.2`
task_file	TASK.md	Task specification file
task_file_path	./TASK.md	Full path to task file
project_root	Current directory	Project root

Output

Inspection report: .kkachi/{branch_name}/completed/task-inspector-{epoch_timestamp}.md
Verdict: PASS / PARTIAL / FAIL
Summary: X/Y requirements met, issues found

Difference from task-validator

	task-validator	task-inspector
Model	GLM-4.7	GPT-5.2(-Codex)
Purpose	Pre-PR quick check	Deep verification
Depth	Surface matching	Semantic analysis
Cost	Low	Medium-High

Notes

Subagent uses Codex in read-only sandbox
Results are verified before reporting
Ensure .kkachi/ is in .gitignore

Name	17th-task-inspector
Description	Use this skill for deep inspection of implementation against TASK.md using GPT-5.2-Codex. Provides thorough cross-model verification with detailed pass/fail analysis. Appropriate for: final verification, critical features, before claiming "done". Not appropriate for: quick checks (use task-validator), style review, test execution.

17th-task-inspector

SKILL.md