checklisted
Install: claude install-skill alternative-intelligence-cp/claude-skills
# The checks
**Every hole this discipline has found was found by a check that diffs two
lists, and none of them by a test.** These are those diffs. They are scripts
with exit codes, not careful readings, and each ships a negative control
beside it because *a check that has never failed has not been shown to work*
(P-35).
All four exit `0` clean, `1` findings, `2` could not run, and read
**git-tracked files only** — so scratch work is never a finding, and a file
you have not committed yet is invisible to them.
```bash
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check_trace.py" <project>
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check_refs.py" <project>
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check_report.py" <project> T-n[.S-m]
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/check_scope.py" <project> [T-n[.S-m]]
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/run_controls.py" # prove the checks
```
## What each finding means
### `check_trace` — goal to requirement to task to evidence
| Finding | What it is, and what to do |
|---|---|
| `orphan-scope` | a charter goal no requirement covers. You promised the client something nobody owns |
| `uncovered-requirement` | a requirement no task will implement. It will silently not happen |
| `unmotivated-task` | a task discharging no requirement. **Either scope creep, or a requirement nobody wrote down** — and the second is far more common |
| `unverified-requirement` | a requirement with no runnable acceptance criterion. It will be declared d