Project Audit

project-audit

Triggers: /project-audit, audit project, review claude config, sdd diagnostic, project health check

---

<!-- Structural floor ~440 lines. Add new content to sibling files, not here. -->

Read-only diagnostic of Claude/SDD config. Flow: /project-audit → audit-report.md → /project-fix → /project-audit (verify). The report IS the spec /project-fix implements. Kernel: discovery → evaluation → report (stable; rules evolve). Save report at [project_root]/.claude/audit-report.md.

Sibling reference files — REPORT_TEMPLATE.md (output format), SCORING.md (100-point distribution + interpretation), PHASE_A_SCRIPT.md (discovery script + schema).

Dimension classes

D5 was removed. Informational dimensions never affect score unless stated.

Compatibility policy — global-config exemptions

IS_GLOBAL_CONFIG=1 → the methodology repo is not a consumer of its own deployment. Skip table:

Rationale: ai-context/ is deployed BY this repo INTO consumer projects via /project-setup — auditing the methodology repo for it is a category error. Scoring: D2 → N/A; denominator becomes 75. Final = round(actual/75*100).

---

Process

Read real files. Never assume. Run dimensions systematically.

Phase A — Discovery

Run PHASE_A_SCRIPT.md once; capture key=value outputs; run the post-script "Legacy commands/ detection". Max 3 Bash calls total per audit run.

Phase B — Per-dimension evaluation

Apply each dimension. Findings carry severity (CRITICAL/HIGH/MEDIUM/LOW/INFO) and optional FIX_MANIFEST entries.

Dimension 1 — CLAUDE.md

Project type detection: IS_GLOBAL_CONFIG=1 → global-config. Accept root CLAUDE.md as equivalent to .claude/CLAUDE.md. Note Project Type in report.

Stack severity is CRITICAL per ADR-004 (every tech-reference skill routes on it). Exemptions under IS_GLOBAL_CONFIG=1: see "Compatibility policy".

Stack comparison: extract top 5–10 deps from package.json/equivalent, compare with CLAUDE.md. Report discrepancies as declared X.Y, actual A.B.

Template path verification: locate ## Documentation Conventions section, extract paths matching docs/templates/*.md, verify each exists. Each missing → MEDIUM + required_actions.medium type: create_file. Skip entirely if no such pattern found.

---

Dimension 2 — Memory (ai-context/)

Skip entirely when IS_GLOBAL_CONFIG=1 — emit INFO "D2 skipped — global-config repos do not use ai-context/". D2 → N/A (25 pts excluded from denominator). See Compatibility policy.

For standard projects:

Location may be ai-context/ or docs/ai-context/. Check both.

Content checks (per existing file):

• stack.md: top-5 dependency versions match package.json.
• architecture.md: directories named exist on disk.
• conventions.md: documented conventions appear in 2–3 sample real files.
• known-issues.md: real content vs. [To confirm]/[Empty] stubs.
• changelog-ai.md: at least one ## YYYY-MM-DD entry.

Placeholder phrase detection — scan content for (case-insensitive in brackets, case-sensitive for plain TODO): [To be filled], [empty], [TBD], [placeholder], [To confirm], [Empty], plain uppercase TODO. Each match → HIGH "[filename] appears to contain unfilled placeholder content". Treat the file as functionally empty even if line count passes. Add to required_actions.high with type: update_file.

stack.md version count — count lines matching x.y, x.y.z, or vX. < 3 → MEDIUM "stack.md lists fewer than 3 technologies with concrete versions — minimum is 3". Skip when stack.md absent or already placeholder.

User documentation freshness (for ai-context/scenarios.md and ai-context/quick-reference.md):

• Absent → LOW "[filename] missing — create via /project-onboard or manually".
• Present → search first 10 lines for ^> Last verified: (\d{4}-\d{2}-\d{2})$.

Missing/malformed → LOW. > 90 days old → LOW with age. All findings LOW, no D2 score deduction.

---

Dimension 3 — SDD Orchestrator

3a. Global SDD skills — 8 phase skills must exist in ~/.claude/skills/: sdd-explore, sdd-propose, sdd-spec, sdd-design, sdd-tasks, sdd-apply, sdd-verify, sdd-archive. Any missing → CRITICAL.

3b. Engram availability — call mem_context. Reachable → INFO log. Unreachable → HIGH "Engram not reachable — SDD artifacts will not persist".

3c. CLAUDE.md mentions SDD — contains any /sdd-* → HIGH if absent; section explaining SDD flow → LOW if absent.

3d. Orphaned changes — mem_search(query: "sdd/", project: "{project}"), filter for state artifacts with last_updated > 14 days ago and no archive-report. List them.

3e. Hook script existence — for each settings file present (settings.json, .claude/settings.json, settings.local.json), locate hooks key and extract script paths. Each missing on disk → HIGH + required_actions.high type: create_file. Skip when no hooks key.

3f. Active changes conflict detection: 1. Search engram for active changes (no archive-report). Retrieve each design.md. 2. Locate ## File Change Matrix table. Extract File column. Normalize: lowercase + strip leading ./. 3. Skip if fewer than 2 active changes have a design.md. 4. Intersect path sets. Each overlap → MEDIUM "Concurrent file modification conflict: [path] is targeted by both [change-A] and [change-B]". Add to violations[], rule: "D3-active-changes-conflict".

Normalization only handles lowercase + leading ./. Other format inconsistencies are not caught.

---

Dimension 4 — Skills quality

4a. Registry vs disk (bidirectional): each skill in CLAUDE.md exists on disk; each skill on disk appears in CLAUDE.md. Report mismatches both ways.

Skip 4a when IS_GLOBAL_CONFIG=1 (no manual registry exists; Principle 2). Emit INFO "D4a skipped — harness auto-discovery, not a manual registry". 4b and 4c still apply.

4b. Minimum content — for each skill file:

• < 30 lines → probable stub.
• Format-aware structural check (see docs/format-types.md):

1. Parse YAML frontmatter, extract format:. Absent → treat as procedural. 2. Unknown value → INFO, treat as procedural.

Missing **Triggers** or ## Rules → MEDIUM for all formats. Missing ## Process is NOT a finding for reference/anti-pattern.

Each finding → required_actions.medium, type: skill_quality_action, action_type: add_missing_section, target: [skill path], missing_sections: ["[heading]"].

4c. Relevant tech skills coverage (scored 0–10 pts):

Stack → skill mapping: React 18+ → react-19, Next.js 14+ → nextjs-15, TypeScript → typescript, Zustand → zustand-5, Tailwind → tailwind-4, Zod → zod-4, Playwright → playwright, Prisma → prisma, React Native / Expo → react-native, Go → go-testing.

Coverage rule (tech-skill locality policy): a skill counts as "covered" if it exists EITHER in the project's local .claude/skills/<name>/ OR in the global ~/.claude/skills/<name>/. Tech skills are expected to live locally; only meta/orchestrator skills are expected globally. Penalizing a project for not having zod-4 globally when it has it locally is a category error.

"Applicable" = project uses the tech AND a matching skill exists locally or globally. D4 max: 20 pts (4a+4b = 10; 4c = 10).

---

Dimension 6 — Cross-reference integrity

Everything referenced in the Claude configuration must exist on disk.

Each broken reference: source file, approximate line, missing path.

---

Dimension 7 — Architecture compliance

Input: analysis-report.md at project root (produced by /project-analyze).

Staleness penalty (when ANALYSIS_REPORT_EXISTS=1):

Emit "analysis-report.md is [N] days old — staleness penalty applied". Stacks with drift; combined floor 0.

When drift is minor/significant, read ## Architecture Drift from the report and list entries.

D7 violations go in violations[] only — NOT required_actions. /project-fix does not auto-fix architecture drift.

---

Dimension 8 — Testing & verification

8a. Test runner configured or detectable → HIGH if missing. Documented testing strategy in ai-context/ → MEDIUM if missing.

8b. For each archive-report in engram, verify a verify-report exists and references tool execution results. Missing → HIGH.

8c. For each active change with tasks, verify the task plan includes verification criteria. For each with design, verify the design defines test approach.

---

Dimension 9 — Project skills quality (informational)

Skip when $LOCAL_SKILLS_DIR does not exist — emit "No [value] directory found — Dimension 9 skipped". No deduction.

Global-config circular detection: when auditing the global-config repo, every subdir under skills/ has a matching counterpart in ~/.claude/skills/ (same files via install.sh). Disposition keep for all — expected.

D9-2 Duplicate — for each subdir under $LOCAL_SKILLS_DIR: ~/.claude/skills/<name>/ exists → disposition move-to-global (if differs) or delete (if identical). Global catalog unreadable → INFO, disposition keep.

D9-3 Structural completeness — apply D4b format-aware check. Missing required section OR missing SKILL.md → disposition update, action add_missing_section.

D9-4 Language compliance — D4e heuristic on body text outside fenced code. Non-English prose → disposition update, action flag_language_violation, severity INFO (no deduction).

D9-5 Stack relevance — technology references in trigger line and title. If absent from both ai-context/stack.md AND package.json/pyproject.toml → disposition update, action flag_irrelevant, severity INFO. No stack source → emit "Stack relevance check skipped — no stack source found".

---

Dimension 10 — Feature docs coverage (informational)

Skip when no features detected.

Config-driven — if project config.yaml has feature_docs: key, read convention (skill|markdown|mixed), paths, and feature_detection.

Heuristic fallback — sources, in order: 1. Non-SDD skills in $LOCAL_SKILLS_DIR (names not starting with sdd-, project-, memory-, skill-). 2. *.md files in docs/features/ or docs/modules/. 3. Subdirs of src/features/, src/modules/, app/ with a README.md.

Exclude always: shared, utils, common, lib, types, hooks, components. Empty after exclusions → emit "No feature directories detected — Dimension 10 skipped".

Per-feature checks:

• D10-a Coverage: PASS if doc exists per convention; FAIL otherwise.
• D10-b Structure: SKILL.md → PASS if frontmatter + **Triggers** +

## Process + ## Rules. Other .md → PASS if H1 + ≥1 H2.

• D10-c Freshness: extract paths /src/[^\s]+, /lib/[^\s]+,

/app/[^\s]+. Each missing → flag stale.

• D10-d Registry alignment: SKILL.md in .claude/skills/ not in CLAUDE.md

registry → INFO (not a warning).

D10 findings MUST NOT appear in required_actions or skill_quality_actions.

---

Dimension 11 — Internal coherence (informational)

Read/Glob/Grep only — no Bash. Skip when neither $LOCAL_SKILLS_DIR nor root CLAUDE.md exists.

D11-a Count consistency — extract claims via CLAIM_PATTERN = /(\d+)\s+(Dimensions?|Steps?|Rules?|Phases?|Checks?|Sub-checks?)/i from headings and blockquote lines. Count matching body sections. Mismatch → INFO. Do NOT match inside code blocks.

D11-b Numbering continuity — patterns: /^#{2,3}\s+.*Step\s+(\d+)/im, Dimension\s+(\d+), Phase\s+(\d+), /^#{2,4}\s+.*D(\d+)/m. Sort numbers, detect gaps and duplicates. ≥ 2 members required. Severity INFO.

D11-c Frontmatter-body alignment — if description has a numeric claim, verify via D11-a logic. Mismatch → INFO.

All D11 findings → violations[], severity info, rule names D11-count-consistency, D11-numbering-continuity, D11-frontmatter-body. Never in required_actions.

---

Dimension 12 — ADR coverage (informational)

Activation: CLAUDE.md contains string docs/adr/. If absent → emit INFO, skip.

D12-1: ADR_README_EXISTS=0 → HIGH "CLAUDE.md references docs/adr/ but docs/adr/README.md is missing" + required_actions.high type: create_file.

D12-2: Glob docs/adr/NNN-*.md. No matches → INFO "docs/adr/ contains no ADR files yet". Each ADR: search ## Status heading or frontmatter status: field. Neither → MEDIUM "ADR file [filename] is missing a valid status field" + required_actions.medium type: update_file. Valid: accepted, deprecated, superseded; custom allowed, do not validate value.

---

Dimension 13 — Spec coverage (informational)

Activation: Engram reachable AND mem_search(query: "sdd/") returns spec artifacts.

D13-1: For each spec.md, extract path-like references (contain /, no spaces, not in URLs or fenced code). Check existence at [project_root]/[path]. Missing → INFO "Spec artifact references a path that no longer exists: [path]". Add to violations[], rule: "D13-stale-path-reference", severity: "info", file: "engram spec artifact". INFO findings NOT in required_actions.

---

Dimension 14 — Budget compliance (informational)

Runs on every audit.

1. Read CLAUDE.md at project root; count characters. 2. Global-config (install.sh + sync.sh exist) → 20,000 char budget; otherwise → 5,000. 3. Over budget → INFO "CLAUDE.md is [N] chars ([N-budget] over [budget] budget). Consider extracting content to skills (ADR-041)". 4. Within → INFO "CLAUDE.md budget OK: [N]/[budget] chars".

Findings go in ## Budget Compliance section. No score impact.

---

Report

Save at [project_root]/.claude/audit-report.md using the exact structure in REPORT_TEMPLATE.md. Scoring distribution and interpretation live in SCORING.md.

---

Rules

1. Always read real files. Never assume content. 2. Run in a subagent with read tools. Never in main context. 3. Always save the report at .claude/audit-report.md before presenting. 4. The FIX_MANIFEST is valid YAML. Verify the block parses. 5. Never modify anything. 100% read-only. 6. If a file cannot be read, report ❌ with the exact error. Do not assume absence. 7. When finished: "Report saved in .claude/audit-report.md. To implement: /project-fix". 8. All shell discovery in Phase A. Max 3 Bash calls per run. No per-dimension ls/grep/wc -l/find. 9. Compatibility behavior is explicit, not implicit in a dimension.

project-audit — Phase A Discovery Script

Reference file consumed by SKILL.md. Phase A is the single consolidated

shell call that gathers all structural facts from the project. Maximum 3

total Bash calls per audit run; this script counts as 1.

Reference script

#!/usr/bin/env bash
# project-audit discovery — Phase A
# Usage: bash <(echo "$SCRIPT") [project_root]
PROJECT="${1:-.}"
f() { [ -f "$PROJECT/$1" ] && echo 1 || echo 0; }
d() { [ -d "$PROJECT/$1" ] && echo 1 || echo 0; }
lc() { [ -f "$PROJECT/$1" ] && wc -l < "$PROJECT/$1" || echo 0; }

echo "CLAUDE_MD_EXISTS=$(f .claude/CLAUDE.md)"
echo "ROOT_CLAUDE_MD_EXISTS=$(f CLAUDE.md)"
echo "ENGRAM_REACHABLE=<check via mem_context>"
echo "INSTALL_SH_EXISTS=$(f install.sh)"
echo "SYNC_SH_EXISTS=$(f sync.sh)"

# Global-config detection for LOCAL_SKILLS_DIR
if [ "$INSTALL_SH_EXISTS" = "1" ] && [ "$SYNC_SH_EXISTS" = "1" ]; then
  LOCAL_SKILLS_DIR="skills"
  IS_GLOBAL_CONFIG=1
elif [ -d "$PROJECT/skills/_shared" ]; then
  LOCAL_SKILLS_DIR="skills"
  IS_GLOBAL_CONFIG=1
else
  LOCAL_SKILLS_DIR=".claude/skills"
  IS_GLOBAL_CONFIG=0
fi
echo "LOCAL_SKILLS_DIR=$LOCAL_SKILLS_DIR"
echo "IS_GLOBAL_CONFIG=$IS_GLOBAL_CONFIG"

echo "STACK_MD_EXISTS=$(f ai-context/stack.md)"
echo "ARCH_MD_EXISTS=$(f ai-context/architecture.md)"
echo "CONV_MD_EXISTS=$(f ai-context/conventions.md)"
echo "ISSUES_MD_EXISTS=$(f ai-context/known-issues.md)"
echo "CHANGELOG_MD_EXISTS=$(f ai-context/changelog-ai.md)"
echo "CLAUDE_MD_LINES=$(lc CLAUDE.md)"
echo "STACK_MD_LINES=$(lc ai-context/stack.md)"

# Orphaned changes — detected via engram search for stale SDD state artifacts
ORPHANED="<detected via mem_search for sdd/*/state artifacts older than 14 days>"
echo "ORPHANED_CHANGES=${ORPHANED:-NONE}"

# SDD phase skills present
SDD_COUNT=0
for phase in explore propose spec design tasks apply verify archive; do
  [ -f "$HOME/.claude/skills/sdd-$phase/SKILL.md" ] && SDD_COUNT=$((SDD_COUNT+1))
done
echo "SDD_SKILLS_PRESENT=$SDD_COUNT"
echo "FEATURE_DOCS_CONFIG_EXISTS=<check config.yaml at project root if it exists>"
echo "ANALYSIS_REPORT_EXISTS=$(f analysis-report.md)"
echo "ANALYSIS_REPORT_DATE=$(head -5 "$PROJECT/analysis-report.md" 2>/dev/null | grep 'Last analyzed:' | awk '{print $3}' || echo '')"
echo "ROOT_SETTINGS_JSON_EXISTS=$(f settings.json)"
echo "DOTCLAUDE_SETTINGS_JSON_EXISTS=$(f .claude/settings.json)"
echo "SETTINGS_LOCAL_JSON_EXISTS=$(f settings.local.json)"
echo "ADR_DIR_EXISTS=$(d docs/adr)"
echo "ADR_README_EXISTS=$(f docs/adr/README.md)"
echo "ENGRAM_HAS_SPECS=<check via mem_search for sdd/*/spec artifacts>"

Output key schema

Each key is a key=value line in stdout:

• CLAUDE_MD_EXISTS — 1 if .claude/CLAUDE.md exists, 0 if absent
• ROOT_CLAUDE_MD_EXISTS — 1 if root CLAUDE.md exists, 0 if absent
• ENGRAM_REACHABLE — 1 if Engram MCP is reachable, 0 if not
• INSTALL_SH_EXISTS — 1 if install.sh exists at project root, 0 if absent
• SYNC_SH_EXISTS — 1 if sync.sh exists at project root, 0 if absent
• LOCAL_SKILLS_DIR — string: "skills" (global-config detected via Condition A or B) or ".claude/skills" (standard project)
• IS_GLOBAL_CONFIG — 1 if the project IS the global-config repo itself (install.sh + sync.sh, OR skills/_shared/ present); 0 for any other project. Used by D1, D2, D4a to skip checks that don't apply when auditing the methodology repo itself.
• STACK_MD_EXISTS — 1 if ai-context/stack.md exists, 0 if absent
• ARCH_MD_EXISTS — 1 if ai-context/architecture.md exists, 0 if absent
• CONV_MD_EXISTS — 1 if ai-context/conventions.md exists, 0 if absent
• ISSUES_MD_EXISTS — 1 if ai-context/known-issues.md exists, 0 if absent
• CHANGELOG_MD_EXISTS — 1 if ai-context/changelog-ai.md exists, 0 if absent
• CLAUDE_MD_LINES — integer line count of root CLAUDE.md (0 if absent)
• STACK_MD_LINES — integer line count of ai-context/stack.md (0 if absent)
• ORPHANED_CHANGES — comma-separated names of orphaned change dirs, or NONE
• SDD_SKILLS_PRESENT — integer count of present ~/.claude/skills/sdd-*/SKILL.md files (0–8)
• FEATURE_DOCS_CONFIG_EXISTS — 1 if project config.yaml contains a feature_docs: key, 0 if absent
• ANALYSIS_REPORT_EXISTS — 1 if analysis-report.md exists at project root, 0 if absent
• ANALYSIS_REPORT_DATE — ISO date string from the Last analyzed: field of analysis-report.md, or empty string if absent
• ROOT_SETTINGS_JSON_EXISTS — 1 if settings.json exists at project root, 0 if absent
• DOTCLAUDE_SETTINGS_JSON_EXISTS — 1 if .claude/settings.json exists, 0 if absent
• SETTINGS_LOCAL_JSON_EXISTS — 1 if settings.local.json exists at project root, 0 if absent
• ADR_DIR_EXISTS — 1 if docs/adr/ directory exists, 0 if absent
• ADR_README_EXISTS — 1 if docs/adr/README.md exists, 0 if absent
• ENGRAM_HAS_SPECS — 1 if engram contains spec artifacts for this project, 0 if absent

Legacy commands/ detection (post-script check)

After running Phase A, check whether .claude/commands/ exists in the project root:

if [ -d "$PROJECT/.claude/commands" ]; then
  emit LOW finding: "Legacy .claude/commands/ directory detected — migrate to .claude/skills/ following the official Claude Code standard."
fi

• Severity: LOW (informational)
• Score penalty: none
• FIX_MANIFEST entry: none (do NOT add a required_actions entry for this finding)

Phase A extension — analysis-report.md

After Phase A completes, two variables are available for Dimension 7 in Phase B:

• ANALYSIS_REPORT_EXISTS — 1 if analysis-report.md exists at the project root, 0 if absent
• ANALYSIS_REPORT_DATE — ISO date string from the Last analyzed: field, or empty string if absent

Important constraints:

• project-audit does NOT invoke project-analyze automatically. analysis-report.md is treated as external input produced by a prior /project-analyze run.
• D7 in Phase B reads ANALYSIS_REPORT_EXISTS and ANALYSIS_REPORT_DATE to compute its score and staleness warning.
• These variables are added to the existing Phase A script — no additional Bash call is introduced. Total Bash calls per audit run remain ≤ 3.

project-audit — Report Template

Reference file consumed by SKILL.md. The audit writes its output to

.claude/audit-report.md using the exact structure below. Placeholders in

square brackets are filled at generation time.

---

`````markdown

Audit Report — [Project Name]

Generated: [YYYY-MM-DD HH:MM] Score: [XX/100] SDD Ready: [YES|NO|PARTIAL]

---

FIX_MANIFEST

<!-- This block is consumed by /project-fix — DO NOT modify manually -->

score: [XX]
sdd_ready: [true|false|partial]
generated_at: "[timestamp]"
project_root: "[absolute path]"

required_actions:
  critical:
    - id: "[unique-id]"
      type: "[create_file|update_file|create_dir|add_registry_entry|install_skill]"
      target: "[path or element]"
      reason: "[why it is necessary]"
      template: "[template_name if applicable]"
  high:
    - id: "[unique-id]"
      type: "..."
      target: "..."
      reason: "..."
  medium:
    - ...
  low:
    - ...

missing_global_skills:
  - "[skill-name]"

orphaned_changes:
  - name: "[name]"
    last_phase: "[phase]"
    days_inactive: [N]

violations:
  - file: "[path]"
    line: [N]
    rule: "[violated rule]"
    severity: "[critical|high|medium]"

skill_quality_actions:
  - id: "D9-<skill-name>-<action-type>"
    skill_name: "<name>"
    local_path: ".claude/skills/<name>/SKILL.md"
    global_counterpart: "~/.claude/skills/<name>/SKILL.md"
    action_type: "delete_duplicate|add_missing_section|flag_irrelevant|flag_language"
    disposition: "delete|move-to-global|update|keep"
    missing_sections: ["## Rules", "## Process"]
    detail: "<human-readable reason>"
    severity: "info|warning"

---

Executive Summary

[3-5 lines describing the general state of the project from the Claude/SDD perspective]

---

Score: [XX]/100

SDD Readiness: [FULL / PARTIAL / NOT CONFIGURED]

• FULL: Engram reachable, CLAUDE.md mentions /sdd-*, global skills present
• PARTIAL: Some SDD elements present but incomplete
• NOT CONFIGURED: Engram not reachable and no SDD references in CLAUDE.md

---

Dimension 1 — CLAUDE.md [OK|WARNING|CRITICAL]

Stack Discrepancies: [List each discrepancy: "Declares React 18, actual ^19.0.0"]

Template path verification:

[or: "No docs/templates/*.md paths found in CLAUDE.md — check skipped"]

---

Dimension 2 — Memory [OK|WARNING|CRITICAL]

Coherence issues detected: [List specific issues with file + what is outdated]

Placeholder phrase detection:

[or: "No placeholder phrases detected"]

stack.md technology count: [N] version entries detected (minimum: 3) — ✅/⚠️

---

Dimension 3 — SDD Orchestrator [OK|WARNING|CRITICAL]

Global SDD Skills:

Engram availability:

CLAUDE.md mentions SDD: ✅/❌

Orphaned changes: [none | list]

Hook script existence:

[or: "No hooks key found in settings files — check skipped"]

Active changes — file conflict detection:

[or: "No conflicts detected"] [or: "Fewer than two active changes have design.md — check skipped"]

---

Dimension 4 — Skills [OK|WARNING|CRITICAL]

Skills in registry but not on disk: [list or "none"]

Skills on disk but not in registry: [list or "none"]

Skills with insufficient content (<30 lines): [list or "none"]

Recommended global tech skills not installed: [list with install command: /skill-add name]

---

Dimension 6 — Cross-references [OK|WARNING|CRITICAL]

Broken references:

[list or "none"]

---

Dimension 7 — Architecture Compliance [OK|WARNING|CRITICAL]

Analysis report found: YES/NO Last analyzed: [date or N/A] Report age: [N days | N/A] Architecture drift status: [none|minor|significant|N/A] Staleness penalty: [none | −1 pt (report is [N] days old, > 30 days) | −2 pts (report is [N] days old, > 60 days)]

Drift entries: (when drift is present)

---

Dimension 8 — Testing & Verification [OK|WARNING|CRITICAL]

Project has test runner: ✅/❌

Archived changes without verify-report: [list or "none"]

Archived changes with empty verify-report.md (without [x]): [list or "none"]

Verify rules are executable: ✅/⚠️/❌

---

Dimension 9 — Project Skills Quality [OK|INFO|SKIPPED]

Local skills directory: [value of $LOCAL_SKILLS_DIR] — [N skills found | not found — skipped]

Skills with missing structural sections: [list or "none"] Language violations (INFO — manual fix required): [list or "none"] Stack relevance issues (INFO): [list or "none"]

_Note: Dimension 9 does not affect the score in this iteration. Findings are informational unless action_type is delete_duplicate._

---

Dimension 10 — Feature Docs Coverage [OK|INFO|SKIPPED]

Detection mode: configured | heuristic | skipped Features detected: [N] ([list of names])

_D10 findings are informational only — they do not affect the score and are not auto-fixed by /project-fix._

---

Dimension 11 — Internal Coherence [OK|INFO|SKIPPED]

Skills scanned: [N] from $LOCAL_SKILLS_DIR

Inconsistencies found: [N] across [M] skills (or "None — all skills internally coherent")

_D11 findings are informational only — they do not affect the score and are not auto-fixed by /project-fix._

---

Dimension 12 — ADR Coverage [OK|INFO|SKIPPED]

Condition: CLAUDE.md references docs/adr/ — YES/NO ADR README exists: ✅/❌ ADRs scanned: [N]

[or: "ADR Coverage check skipped — docs/adr/ not referenced in CLAUDE.md"] [or: "docs/adr/ contains no ADR files yet"]

_D12 findings are informational only — no score impact._

---

Dimension 13 — Spec Coverage [OK|INFO|SKIPPED]

Condition: Engram reachable and spec artifacts found — YES/NO Domains detected: [list of domain names]

[or: "Spec Coverage check skipped — no spec artifacts found in engram"]

_D13 findings are informational only — no score impact._

---

Budget Compliance [INFO]

Project type: agent-config (20,000 char global budget) | other project (5,000 char project budget)

CLAUDE.md character count: [N] chars — [OK: N/budget | OVER: N chars over budget]

_Budget Compliance findings are informational only — no score impact. See ADR-041 for budget governance details._

---

Required Actions

Critical (block SDD):

1. [concrete action] → run /project-fix or manually: [instruction]

High (degrade quality):

1. [concrete action]

Medium:

1. [concrete action]

Low (optional improvements):

1. [concrete action]

---

_To implement these corrections: run /project-fix_ _This report was generated by /project-audit — do not modify the FIX_MANIFEST block manually_ `````

project-audit — Scoring Rubric

Reference file consumed by SKILL.md. Defines the 100-point distribution

across scored dimensions, informational-only dimensions, and the score

interpretation table.

Dimension scoring table

Global-config exemptions

When Phase A reports IS_GLOBAL_CONFIG=1, two scored dimensions become N/A because they describe consumer-project structure, not methodology-repo structure (see "Compatibility policy" in SKILL.md for the full rationale):

Recompute the denominator: max = 100 - 25 = 75. Final score: round((actual / 75) * 100). Report the table with D2 existence: N/A and D2 quality: N/A and a footnote: "D2 excluded — global-config repo (see config-guidelines Principle 1)."

D4a (registry vs disk, sub-criterion of D4) is also skipped under IS_GLOBAL_CONFIG=1, but D4 keeps its 20-point max (4b + 4c cover content depth and global tech skills coverage, both still applicable).

Score interpretation

SDD Readiness flag

Independent from the numeric score. Set as follows:

• FULL — Engram reachable, CLAUDE.md mentions /sdd-*, all 8 global SDD skills present.
• PARTIAL — Some SDD elements present but at least one of the FULL conditions fails.
• NOT CONFIGURED — Engram not reachable AND no SDD references in CLAUDE.md.