feat(humanizer): update audit/analysis command templates group B [skip-docs]
Wave 5 Step 14. Threads the humanizer vocabulary through the remaining
six audit/analysis command templates and adds a shape test that locks
the structure plus a pair of anchor must-contains.
- commands/drift.md: --raw pass-through; new/resolved/changed-finding
rendering instructions reference userActionLanguage and
relevanceContext rather than raw severity.
- commands/plugin-health.md: --raw pass-through; finding rendering
groups by userImpactCategory and leads with userActionLanguage.
- commands/config-audit.md (router): replaces the 25-line A/B/C/D/F
prose ladder with a humanized stderr-scorecard reference + three
userActionLanguage-grouped "What you can do next" branches; --raw
threaded through both scan-orchestrator and posture invocations.
- commands/discover.md: --raw pass-through; finding-summary rendering
groups by userImpactCategory.
- commands/analyze.md: --raw pass-through; analyzer-agent prompt now
instructs grouping by userImpactCategory and leading with
userActionLanguage; humanized title/description/recommendation
strings rendered verbatim, no paraphrasing.
- commands/status.md: phase-label humanization table — current_phase
machine field name preserved, user-facing labels translated
("Looking at your config files", "Working out what to recommend",
"Asking what you'd like to focus on", "Putting together your action
plan", "Making the changes", "Double-checking everything worked");
--raw preserves verbatim machine field values.
tests/commands/group-b-shape.test.mjs (new, +8 tests, 772 → 780):
- structural: bash block + Read tool + --raw/$ARGUMENTS plumbing
across all 6 files
- findings-renderers: humanized field reference + no grade-prose
- anchor must-contains per plan: config-audit.md ⊇
userImpactCategory|userActionLanguage; drift.md ⊇ --raw|humanized
- status.md: current_phase preserved + ≥3 humanized phase labels
This commit is contained in:
Kjell Tore Guttormsen
parent
79b6e29073
commit
6f38a6340e
7 changed files with 234 additions and 49 deletions
|
|
@ -14,11 +14,15 @@ Generate comprehensive analysis report from discovery findings.
|
|||
- Must have completed Phase 1 (discovery)
|
||||
- Findings must exist in `~/.claude/config-audit/sessions/{session-id}/findings/`
|
||||
|
||||
## Arguments
|
||||
|
||||
- `$ARGUMENTS` may contain `--raw` to forward to the analyzer agent's instructions; in `--raw` mode the agent renders v5.0.0 verbatim severity prefiks instead of humanized `userActionLanguage` urgency phrasing.
|
||||
|
||||
## Implementation
|
||||
|
||||
### Step 1: Verify session state
|
||||
|
||||
Read `~/.claude/config-audit/sessions/{session-id}/state.yaml` and verify discovery phase completed. If not, tell the user: "Discovery hasn't been run yet. Start with `/config-audit discover` or just run `/config-audit` for a full audit."
|
||||
Read `~/.claude/config-audit/sessions/{session-id}/state.yaml` using the Read tool and verify discovery phase completed. If not, tell the user: "Discovery hasn't been run yet. Start with `/config-audit discover` or just run `/config-audit` for a full audit."
|
||||
|
||||
### Step 2: Tell the user what's happening
|
||||
|
||||
|
|
@ -33,18 +37,29 @@ This includes hierarchy mapping, conflict detection, and prioritized recommendat
|
|||
|
||||
Tell the user: **"Generating analysis (this takes about 30 seconds)..."**
|
||||
|
||||
```bash
|
||||
RAW_FLAG=""
|
||||
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
|
||||
```
|
||||
|
||||
```
|
||||
Agent(subagent_type: "config-audit:analyzer-agent")
|
||||
model: sonnet
|
||||
prompt: |
|
||||
Analyze all findings in: ~/.claude/config-audit/sessions/{session-id}/findings/
|
||||
Mode: $RAW_FLAG (empty = humanized; "--raw" = v5.0.0 verbatim severity prefiks)
|
||||
Generate comprehensive report covering:
|
||||
1. Executive summary with key metrics
|
||||
1. Executive summary with key metrics, grouped by userImpactCategory
|
||||
2. Hierarchy map visualization
|
||||
3. Conflict detection across config layers
|
||||
4. CLAUDE.md quality assessment
|
||||
5. Security issues (secrets, permissions)
|
||||
6. Top 10 prioritized recommendations
|
||||
6. Top 10 prioritized recommendations — lead each item with the
|
||||
finding's userActionLanguage ("Fix this now," "Fix soon,"
|
||||
"Fix when convenient," "Optional cleanup," "FYI") rather than
|
||||
raw severity. The humanizer already replaced jargon-heavy
|
||||
title/description/recommendation strings with plain-language
|
||||
equivalents — render them verbatim, do not paraphrase.
|
||||
Output to: ~/.claude/config-audit/sessions/{session-id}/analysis-report.md
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -82,10 +82,12 @@ This is a silent infrastructure step — do NOT show output to the user.
|
|||
|
||||
Tell the user: **"Running 12 configuration scanners..."**
|
||||
|
||||
Run both scanners and posture in a single Bash command:
|
||||
Run both scanners and posture in a single Bash command. Default mode runs the humanizer, so each finding in `scan-results.json` carries `userImpactCategory`, `userActionLanguage`, and `relevanceContext` alongside the v5.0.0 fields. If the user passed `--raw`, thread it through to both CLIs to get v5.0.0 verbatim output.
|
||||
|
||||
```bash
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/scan-orchestrator.mjs <target-path> --output-file ~/.claude/config-audit/sessions/{session-id}/findings/scan-results.json [--full-machine] [--global] 2>/dev/null; node ${CLAUDE_PLUGIN_ROOT}/scanners/posture.mjs <target-path> --json --output-file ~/.claude/config-audit/sessions/{session-id}/posture.json [--full-machine] [--global] 2>/dev/null; echo $?
|
||||
RAW_FLAG=""
|
||||
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/scan-orchestrator.mjs <target-path> --output-file ~/.claude/config-audit/sessions/{session-id}/findings/scan-results.json [--full-machine] [--global] $RAW_FLAG 2>/dev/null; node ${CLAUDE_PLUGIN_ROOT}/scanners/posture.mjs <target-path> --output-file ~/.claude/config-audit/sessions/{session-id}/posture.json [--full-machine] [--global] $RAW_FLAG 2>/dev/null; echo $?
|
||||
```
|
||||
|
||||
Use `--full-machine` for `full` scope, `--global` for `home` scope. For `repo` and `current`, pass the resolved path directly.
|
||||
|
|
@ -134,19 +136,14 @@ Write to: `~/.claude/config-audit/sessions/{session-id}/state.yaml`
|
|||
|
||||
### Step 6: Display results
|
||||
|
||||
Present results using this template. Replace all placeholders with actual values. **Adapt the summary sentence based on grade.**
|
||||
Present results using this template. The humanizer has already replaced jargon-heavy `title`/`description`/`recommendation` strings on every finding with plain-language equivalents — render them verbatim. Lead urgency phrasing with `userActionLanguage` ("Fix this now", "Fix soon", "Fix when convenient", "Optional cleanup", "FYI") and group "What you can do next" suggestions by that field. Do not re-derive an A/B/C/D/F-to-prose ladder here; the humanized stderr scorecard headline already supplies the grade context, and `userActionLanguage` supplies finding-level urgency.
|
||||
|
||||
```markdown
|
||||
### Results
|
||||
|
||||
**Health: {overallGrade}** | {qualityAreaCount} areas scanned
|
||||
|
||||
{grade-based summary — pick ONE:}
|
||||
- Grade A: "Excellent — your configuration is correct and well-maintained."
|
||||
- Grade B: "Strong — your configuration is solid with minor improvements available."
|
||||
- Grade C: "Decent — your configuration works but has some issues worth addressing."
|
||||
- Grade D: "Needs work — several configuration issues could affect your Claude Code experience."
|
||||
- Grade F: "Significant issues found — addressing these will meaningfully improve your workflow."
|
||||
{Use the headline line from the humanized stderr scorecard — it carries grade-context prose already. Avoid hardcoding a separate per-grade prose ladder.}
|
||||
|
||||
Scanned {files_scanned} files | {real_finding_count} findings ({severity_breakdown})
|
||||
{If test_fixture_count > 0: "({test_fixture_count} additional findings in test fixtures were excluded.)"}
|
||||
|
|
@ -164,26 +161,25 @@ Scanned {files_scanned} files | {real_finding_count} findings ({severity_breakdo
|
|||
| Imports | {grade} | {count} | {status} |
|
||||
| Conflicts | {grade} | {count} | {status} |
|
||||
|
||||
{For the status column, use plain language like: "Well structured", "2 minor issues", "Missing trust levels", "No issues", etc.}
|
||||
{For the status column, use the humanized title from the most-severe finding in that area, or a one-phrase plain-language summary. Findings carry userImpactCategory which already groups by impact bucket — use that vocabulary, not raw scanner names.}
|
||||
|
||||
{If opportunityCount > 0:}
|
||||
{opportunityCount} feature opportunities available — run `/config-audit feature-gap` for context-aware recommendations.
|
||||
|
||||
### What you can do next
|
||||
|
||||
{Include only relevant options based on findings. Explain each one:}
|
||||
Group suggestions by `userActionLanguage` from the humanized findings:
|
||||
|
||||
{If fixable_count > 0:}
|
||||
- **`/config-audit fix`** — Automatically fix {fixable_count} issues. Creates a backup first so you can roll back with one command.
|
||||
{If any finding has userActionLanguage "Fix this now" or "Fix soon":}
|
||||
- **`/config-audit fix`** — auto-fix what's possible (backup created first, one-command rollback). The remaining items go into a prioritized plan.
|
||||
- **`/config-audit plan`** — produce a prioritized action plan for the items that need manual attention.
|
||||
|
||||
{If real findings > fixable_count:}
|
||||
- **`/config-audit plan`** — Get a prioritized action plan for the {remaining} issues that need manual attention.
|
||||
{If most findings are "Fix when convenient" or "Optional cleanup":}
|
||||
- **`/config-audit feature-gap`** — see which features could enhance your setup; pick what you want and implement on the spot.
|
||||
- **`/config-audit fix`** — auto-fix anything deterministic; the rest is genuinely optional.
|
||||
|
||||
{If grade is C or better:}
|
||||
- **`/config-audit feature-gap`** — See which features could help your project, and implement the ones you want on the spot.
|
||||
|
||||
{If grade is D or F:}
|
||||
- **`/config-audit fix`** should be your first step — it handles the most impactful issues automatically.
|
||||
{If only "FYI" findings:}
|
||||
- **`/config-audit feature-gap`** — explore opportunities; nothing is urgent.
|
||||
|
||||
Session saved to: `~/.claude/config-audit/sessions/{session-id}/`
|
||||
```
|
||||
|
|
|
|||
|
|
@ -67,10 +67,12 @@ If `--delta` flag:
|
|||
|
||||
### Step 5: Run discovery
|
||||
|
||||
Run the scan orchestrator silently to discover and scan files:
|
||||
Run the scan orchestrator silently to discover and scan files. Default mode emits humanized JSON — each finding in `scan-results.json` carries `userImpactCategory`, `userActionLanguage`, and `relevanceContext` alongside the v5.0.0 fields. Pass `--raw` through if the user requested it (produces v5.0.0 verbatim envelope; humanizer fields absent).
|
||||
|
||||
```bash
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/scan-orchestrator.mjs <target-path> --output-file ~/.claude/config-audit/sessions/{session-id}/findings/scan-results.json [--full-machine] [--global] 2>/dev/null; echo $?
|
||||
RAW_FLAG=""
|
||||
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/scan-orchestrator.mjs <target-path> --output-file ~/.claude/config-audit/sessions/{session-id}/findings/scan-results.json [--full-machine] [--global] $RAW_FLAG 2>/dev/null; echo $?
|
||||
```
|
||||
|
||||
Check exit code: 0/1/2 → normal. 3 → "Discovery encountered an error. Try a narrower scope."
|
||||
|
|
@ -81,7 +83,7 @@ Write `scope.yaml` and `state.yaml` to session directory. Update state with `cur
|
|||
|
||||
### Step 7: Present summary
|
||||
|
||||
Read the scan results file to count files and findings:
|
||||
Read the scan results file using the Read tool. When you surface initial findings, group them by `userImpactCategory` and lead each line with `userActionLanguage` rather than raw severity prefiks — the humanizer already mapped severity to plain-language phrasing ("Fix this now", "Fix soon", "Fix when convenient", "Optional cleanup", "FYI") so the rest of the toolchain sees consistent wording.
|
||||
|
||||
**Full scan:**
|
||||
```markdown
|
||||
|
|
@ -98,7 +100,7 @@ Read the scan results file to count files and findings:
|
|||
| Hooks | {n} |
|
||||
| Other | {n} |
|
||||
|
||||
Initial scan found {finding_count} items to review.
|
||||
Initial scan found {finding_count} items to review (grouped by impact: {comma-separated counts per userImpactCategory}).
|
||||
|
||||
**Next:** Run `/config-audit analyze` to generate your analysis report.
|
||||
```
|
||||
|
|
|
|||
|
|
@ -16,6 +16,7 @@ Compare current configuration against a saved baseline to see what changed.
|
|||
- A target path (default: current working directory)
|
||||
- `--save`: Save current state as baseline
|
||||
- `--baseline <name>`: Compare against a specific named baseline (default: "default")
|
||||
- `--raw`: Pass-through to the scanner; produces v5.0.0 verbatim diff output (bypasses the humanizer). Use when piping into v5.0.0-baseline diff tooling that depends on byte-stable output.
|
||||
|
||||
## Implementation
|
||||
|
||||
|
|
@ -26,7 +27,9 @@ If `--save` is present:
|
|||
Tell the user: **"Saving current configuration as baseline..."**
|
||||
|
||||
```bash
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <path> --save --name <baseline-name> 2>/dev/null
|
||||
RAW_FLAG=""
|
||||
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <path> --save --name <baseline-name> $RAW_FLAG 2>/dev/null
|
||||
```
|
||||
|
||||
Read stdout for confirmation. Tell the user:
|
||||
|
|
@ -45,17 +48,21 @@ Without `--save`:
|
|||
Tell the user: **"Comparing current configuration against baseline..."**
|
||||
|
||||
```bash
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <path> --baseline <name> 2>/dev/null
|
||||
RAW_FLAG=""
|
||||
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/drift-cli.mjs <path> --baseline <name> $RAW_FLAG 2>/dev/null
|
||||
```
|
||||
|
||||
Read stdout. If baseline not found, tell the user:
|
||||
Read stdout. In default mode the diff sections are humanized — finding titles, descriptions, and recommendations have already been replaced with plain-language equivalents. New/resolved/changed finding lists carry `userImpactCategory`, `userActionLanguage`, and `relevanceContext` so you can group and prioritize without re-deriving severity prose. If `--raw` was passed, the v5.0.0 diff is verbatim — present it in a code block as-is.
|
||||
|
||||
If baseline not found, tell the user:
|
||||
|
||||
```
|
||||
No baseline found. Save one first with:
|
||||
/config-audit drift --save
|
||||
```
|
||||
|
||||
Otherwise, parse and present the drift report:
|
||||
Otherwise, parse and present the drift report. Use the Read tool on the captured stdout (or pipe it into a tmpfile first if you prefer):
|
||||
|
||||
```markdown
|
||||
### Configuration Drift
|
||||
|
|
@ -65,15 +72,15 @@ Otherwise, parse and present the drift report:
|
|||
|
||||
{If new findings:}
|
||||
#### New Issues ({count})
|
||||
| ID | Severity | Description |
|
||||
|----|----------|-------------|
|
||||
| ... | ... | ... |
|
||||
| ID | Action | Description |
|
||||
|----|--------|-------------|
|
||||
| {id} | {userActionLanguage — "Fix this now", "Fix soon", etc.} | {humanized title} |
|
||||
|
||||
{If resolved findings:}
|
||||
#### Resolved ({count})
|
||||
| ID | Description |
|
||||
|----|-------------|
|
||||
| ... | ... |
|
||||
| {id} | {humanized title} |
|
||||
|
||||
{If area changes:}
|
||||
#### Area Changes
|
||||
|
|
@ -82,6 +89,8 @@ Otherwise, parse and present the drift report:
|
|||
| ... | ... | ... | ... |
|
||||
```
|
||||
|
||||
When iterating new/resolved findings, prefer `userActionLanguage` over raw `severity` for the "Action" column — the humanizer already mapped severity to plain-language phrasing, and surfacing it consistently keeps the toolchain coherent. Mention `relevanceContext` when it isn't `affects-everyone` (the user wants to know if a fix touches shared config or just their machine).
|
||||
|
||||
### List baselines
|
||||
|
||||
If `$ARGUMENTS` contains `--list`:
|
||||
|
|
|
|||
|
|
@ -14,6 +14,7 @@ Audit Claude Code plugin structure and quality — validates plugin.json, CLAUDE
|
|||
|
||||
- `$ARGUMENTS` may contain a path to a specific plugin directory
|
||||
- If omitted: scans all plugins in the marketplace root
|
||||
- `--raw`: pass-through to the scanner; produces v5.0.0 verbatim envelope (bypasses the humanizer) for byte-stable diff tooling
|
||||
|
||||
## Implementation
|
||||
|
||||
|
|
@ -31,13 +32,15 @@ Auditing {N} plugin(s) for structure, frontmatter quality, and cross-plugin conf
|
|||
|
||||
### Step 2: Run scanner
|
||||
|
||||
Run silently for each plugin:
|
||||
Run silently for each plugin. Default mode emits a humanized JSON envelope where each PLH finding carries `userImpactCategory`, `userActionLanguage`, and `relevanceContext` alongside the v5.0.0 fields. `--raw` is passed through verbatim when present.
|
||||
|
||||
```bash
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/plugin-health-scanner.mjs <path> 2>/dev/null
|
||||
RAW_FLAG=""
|
||||
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
|
||||
node ${CLAUDE_PLUGIN_ROOT}/scanners/plugin-health-scanner.mjs <path> $RAW_FLAG 2>/dev/null
|
||||
```
|
||||
|
||||
Read stdout output (JSON). Parse findings.
|
||||
Read stdout output (JSON) using the Read tool. Parse findings.
|
||||
|
||||
### Step 3: Present results
|
||||
|
||||
|
|
@ -59,10 +62,12 @@ Read stdout output (JSON). Parse findings.
|
|||
#### Findings by Plugin
|
||||
|
||||
**{plugin-name}** ({finding_count} findings):
|
||||
1. [{id}] {title} — {recommendation}
|
||||
1. [{userActionLanguage}] {humanized title} ({id}) — {humanized recommendation}
|
||||
2. ...
|
||||
```
|
||||
|
||||
Group findings within each plugin by `userImpactCategory` (e.g., "Configuration mistake", "Conflict") and lead each line with `userActionLanguage` ("Fix this now", "Fix soon", "Optional cleanup"). The humanizer already produced the plain-language `title`/`recommendation` strings — render them verbatim, do not paraphrase.
|
||||
|
||||
### Step 4: Suggest next steps
|
||||
|
||||
```
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: config-audit:status
|
||||
description: Show current session state and available actions
|
||||
allowed-tools: Read, Glob
|
||||
allowed-tools: Read, Glob, Bash
|
||||
model: sonnet
|
||||
---
|
||||
|
||||
|
|
@ -13,18 +13,40 @@ Display current session state and guide next actions.
|
|||
|
||||
```
|
||||
/config-audit status
|
||||
/config-audit status --raw # show the raw v5.0.0 phase identifiers (current_phase: "discover", etc.) instead of humanized labels
|
||||
```
|
||||
|
||||
## Phase-label translation
|
||||
|
||||
The `state.yaml` field `current_phase` is the machine contract — never rename it. The user-facing label is humanized. Map the field value to a plain-language label when rendering (default mode):
|
||||
|
||||
| `current_phase` (machine field, unchanged) | User-facing label |
|
||||
|--------------------------------------------|-------------------|
|
||||
| `discover` | Looking at your config files |
|
||||
| `analyze` | Working out what to recommend |
|
||||
| `interview` | Asking what you'd like to focus on |
|
||||
| `plan` | Putting together your action plan |
|
||||
| `implement` | Making the changes |
|
||||
| `verify` | Double-checking everything worked |
|
||||
|
||||
When `--raw` is in `$ARGUMENTS`, render the raw `current_phase` field value verbatim (no humanization).
|
||||
|
||||
## Implementation
|
||||
|
||||
1. **Find active session**:
|
||||
1. **Parse flags**:
|
||||
```bash
|
||||
RAW_FLAG=""
|
||||
if echo "$ARGUMENTS" | grep -q -- "--raw"; then RAW_FLAG="--raw"; fi
|
||||
```
|
||||
|
||||
2. **Find active session**:
|
||||
```
|
||||
Glob: ~/.claude/config-audit/sessions/*/state.yaml
|
||||
Sort by modification time
|
||||
Use most recent
|
||||
```
|
||||
|
||||
2. **Read session state**:
|
||||
3. **Read session state** with the Read tool:
|
||||
```yaml
|
||||
session_id: "20250126_143022"
|
||||
current_phase: "analyze"
|
||||
|
|
@ -33,7 +55,7 @@ Display current session state and guide next actions.
|
|||
...
|
||||
```
|
||||
|
||||
3. **Display status**:
|
||||
4. **Display status** (default mode — humanized phase labels):
|
||||
```
|
||||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
Config-Audit Session Status
|
||||
|
|
@ -44,11 +66,11 @@ Display current session state and guide next actions.
|
|||
|
||||
PHASE PROGRESS
|
||||
──────────────
|
||||
✓ Phase 1: Discover - 15 files found (current directory)
|
||||
✓ Phase 2: Analyze - report generated
|
||||
○ Phase 3: Interview - not started (optional)
|
||||
○ Phase 4: Plan - not started
|
||||
○ Phase 5: Implement - not started
|
||||
✓ Phase 1: Looking at your config files - 15 files found (current directory)
|
||||
✓ Phase 2: Working out what to recommend - report generated
|
||||
○ Phase 3: Asking what you'd like to focus on - not started (optional)
|
||||
○ Phase 4: Putting together your action plan - not started
|
||||
○ Phase 5: Making the changes - not started
|
||||
|
||||
NEXT ACTION
|
||||
───────────
|
||||
|
|
@ -64,7 +86,9 @@ Display current session state and guide next actions.
|
|||
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
||||
```
|
||||
|
||||
4. **If no session found**:
|
||||
In `--raw` mode, replace the humanized phase labels with the verbatim machine field values (`Phase 1: discover`, `Phase 2: analyze`, etc.).
|
||||
|
||||
5. **If no session found**:
|
||||
```
|
||||
No active config-audit session found.
|
||||
|
||||
|
|
|
|||
134
plugins/config-audit/tests/commands/group-b-shape.test.mjs
Normal file
134
plugins/config-audit/tests/commands/group-b-shape.test.mjs
Normal file
|
|
@ -0,0 +1,134 @@
|
|||
/**
|
||||
* Wave 5 Step 14 — Group B command-template shape tests.
|
||||
*
|
||||
* Verifies that the 6 audit/analysis command templates in Group B have the
|
||||
* correct structural shape after the humanizer integration:
|
||||
*
|
||||
* - All 6 files: contain a Bash invocation block, reference the Read tool,
|
||||
* and contain the `--raw` flag (or the literal `"$ARGUMENTS"` string).
|
||||
*
|
||||
* - Findings-rendering files (drift.md, plugin-health.md, config-audit.md,
|
||||
* discover.md, analyze.md): reference at least one of
|
||||
* `userImpactCategory|userActionLanguage|relevanceContext`, and do NOT
|
||||
* contain hardcoded grade-prose tables of the form `[ABCDF]\s+grade\s+is`.
|
||||
*
|
||||
* - status.md: phase-label table is present, the machine field name
|
||||
* `current_phase` is preserved (machine contract), and at least one
|
||||
* humanized phase label appears ("Looking at your config files",
|
||||
* "Working out what to recommend", "Putting together your action plan",
|
||||
* "Making the changes", "Double-checking everything worked").
|
||||
*
|
||||
* - Anchor must-contains from plan line 575–579:
|
||||
* - config-audit.md: contains userImpactCategory|userActionLanguage
|
||||
* - drift.md: contains --raw OR humanized
|
||||
*/
|
||||
|
||||
import { test } from 'node:test';
|
||||
import { strict as assert } from 'node:assert';
|
||||
import { readFile } from 'node:fs/promises';
|
||||
import { resolve, dirname } from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
|
||||
const __dirname = dirname(fileURLToPath(import.meta.url));
|
||||
const COMMANDS_DIR = resolve(__dirname, '..', '..', 'commands');
|
||||
|
||||
const GROUP_B_FILES = [
|
||||
'drift.md',
|
||||
'plugin-health.md',
|
||||
'config-audit.md',
|
||||
'discover.md',
|
||||
'analyze.md',
|
||||
'status.md',
|
||||
];
|
||||
|
||||
const FINDINGS_RENDERING_FILES = [
|
||||
'drift.md',
|
||||
'plugin-health.md',
|
||||
'config-audit.md',
|
||||
'discover.md',
|
||||
'analyze.md',
|
||||
];
|
||||
|
||||
const HUMANIZED_FIELD_REGEX = /userImpactCategory|userActionLanguage|relevanceContext/;
|
||||
const RAW_OR_ARGUMENTS_REGEX = /--raw|"\$ARGUMENTS"/;
|
||||
const HARDCODED_GRADE_PROSE_REGEX = /[ABCDF]\s+grade\s+is/;
|
||||
const BASH_BLOCK_REGEX = /```bash\b/;
|
||||
const READ_TOOL_REGEX = /\bRead\s+tool\b|allowed-tools:.*\bRead\b/;
|
||||
|
||||
const HUMANIZED_PHASE_LABELS = [
|
||||
'Looking at your config files',
|
||||
'Working out what to recommend',
|
||||
'Asking what you',
|
||||
'Putting together your action plan',
|
||||
'Making the changes',
|
||||
'Double-checking everything worked',
|
||||
];
|
||||
|
||||
async function readCommand(name) {
|
||||
return await readFile(resolve(COMMANDS_DIR, name), 'utf-8');
|
||||
}
|
||||
|
||||
test('Group B: every file contains a Bash invocation block', async () => {
|
||||
for (const name of GROUP_B_FILES) {
|
||||
const content = await readCommand(name);
|
||||
assert.match(content, BASH_BLOCK_REGEX, `${name} missing bash block`);
|
||||
}
|
||||
});
|
||||
|
||||
test('Group B: every file references the Read tool', async () => {
|
||||
for (const name of GROUP_B_FILES) {
|
||||
const content = await readCommand(name);
|
||||
assert.match(content, READ_TOOL_REGEX, `${name} missing Read tool reference`);
|
||||
}
|
||||
});
|
||||
|
||||
test('Group B: every file contains --raw or "$ARGUMENTS" (pass-through plumbing)', async () => {
|
||||
for (const name of GROUP_B_FILES) {
|
||||
const content = await readCommand(name);
|
||||
assert.match(content, RAW_OR_ARGUMENTS_REGEX, `${name} missing --raw / $ARGUMENTS plumbing`);
|
||||
}
|
||||
});
|
||||
|
||||
test('Group B findings-renderers: reference at least one humanized field', async () => {
|
||||
for (const name of FINDINGS_RENDERING_FILES) {
|
||||
const content = await readCommand(name);
|
||||
assert.match(
|
||||
content,
|
||||
HUMANIZED_FIELD_REGEX,
|
||||
`${name} must reference userImpactCategory, userActionLanguage, or relevanceContext`,
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
test('Group B findings-renderers: no hardcoded grade-prose tables', async () => {
|
||||
for (const name of FINDINGS_RENDERING_FILES) {
|
||||
const content = await readCommand(name);
|
||||
assert.doesNotMatch(
|
||||
content,
|
||||
HARDCODED_GRADE_PROSE_REGEX,
|
||||
`${name} contains a hardcoded "[grade] grade is..." prose table — humanizer owns grade vocabulary now`,
|
||||
);
|
||||
}
|
||||
});
|
||||
|
||||
test('Group B anchor: config-audit.md references userImpactCategory|userActionLanguage', async () => {
|
||||
const content = await readCommand('config-audit.md');
|
||||
assert.match(content, /userImpactCategory|userActionLanguage/);
|
||||
});
|
||||
|
||||
test('Group B anchor: drift.md references --raw or humanized', async () => {
|
||||
const content = await readCommand('drift.md');
|
||||
assert.match(content, /--raw|humanized/);
|
||||
});
|
||||
|
||||
test('status.md: preserves current_phase machine field and adds humanized phase labels', async () => {
|
||||
const content = await readCommand('status.md');
|
||||
// Machine contract preserved
|
||||
assert.match(content, /\bcurrent_phase\b/, 'status.md must keep current_phase as machine field');
|
||||
// At least 3 of the 6 humanized phase labels appear
|
||||
const present = HUMANIZED_PHASE_LABELS.filter(label => content.includes(label));
|
||||
assert.ok(
|
||||
present.length >= 3,
|
||||
`status.md must include at least 3 humanized phase labels; found ${present.length}: ${present.join(', ')}`,
|
||||
);
|
||||
});
|
||||
Loading…
Add table
Add a link
Reference in a new issue