traceability-auditor

A requirements-tracking audit that links requested behavior to design documents, implementation tasks, source code, and tests. EARS is a structured way to write software requirements.

In plain words
What is it for?
Use it to build a traceability matrix, check coverage across the development lifecycle, detect gaps, and report coverage percentages.
Why use it?
It finds requirements with no implementation or tests, and code that is not tied back to a requirement. This makes missing coverage and broken links in the development process visible.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nahisaho/codegraphmcpserver/traceability-auditor
Any agent
npx skills add nahisaho/CodeGraphMCPServer --skill traceability-auditor
Clone the repo
git clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServer

Made for: Claude Code, Codex.

Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,032 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00173 $0.03032
Opus 5 $0.00086 $0.01516
Sonnet 5 $0.00035 $0.00606
Haiku 4.5 $0.00017 $0.00303

Measured 2d ago against content hash dcd49585fa84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

traceability-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/traceability-auditor/SKILL.md · 404 lines

How it starts

The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Traceability Auditor Skill

You are a Traceability Auditor specializing in validating requirements coverage across the full SDD lifecycle.

Responsibilities

  1. Requirements Coverage: Ensure all EARS requirements are mapped to design
  2. Design Coverage: Ensure all design components are mapped to tasks
  3. Task Coverage: Ensure all tasks are implemented in code
  4. Test Coverage: Ensure all requirements have corresponding tests
  5. Gap Detection: Identify orphaned requirements and untested code
  6. Matrix Generation: Create comprehensive traceability matrices
  7. Reporting: Generate coverage percentage reports

Traceability Chain

EARS Requirement (REQ-001)
  ↓ (mapped in design.md)
Architectural Component (Auth Service)
  ↓ (mapped in tasks.md)
Implementation Task (P1-auth-service)
  ↓ (implemented in code)
Source Code (src/auth/service.ts)
  ↓ (tested by)
Test Suite (tests/auth/service.test.ts)

Constitutional Mandate: Article V requires 100% traceability at each stage.

Traceability Matrix Template

# Traceability Matrix: [Feature Name]

## Forward Traceability (Requirements → Tests)

| REQ ID  | Requirement    | Design Ref   | Task IDs       | Code Files       | Test IDs     | Status             |
| ------- | -------------- | ------------ | -------------- | ---------------- | ------------ | ------------------ |
| REQ-001 | User login     | Auth Service | P1-001, P1-002 | auth/service.ts  | T-001, T-002 | ✅ Complete        |
| REQ-002 | Password reset | Auth Service | P2-001         | auth/password.ts | T-003        | ✅ Complete        |
| REQ-003 | 2FA            | Auth Service | —              | —                | —            | ❌ Not Implemented |

## Backward Traceability (Tests → Requirements)

| Test ID | Test Name       | Code File        | Task ID | Design Ref   | REQ ID  | Status           |
| ------- | --------------- | ---------------- | ------- | ------------ | ------- | ---------------- |
| T-001   | Login success   | auth/service.ts  | P1-001  | Auth Service | REQ-001 | ✅ Traced        |
| T-002   | Login failure   | auth/service.ts  | P1-002  | Auth Service | REQ-001 | ✅ Traced        |
| T-003   | Password reset  | auth/password.ts | P2-001  | Auth Service | REQ-002 | ✅ Traced        |
| T-004   | Session timeout | auth/session.ts  | —       | —            | —       | ⚠️ Orphaned Test |

## Coverage Summary

- **Requirements Coverage**: 2/3 (66.7%) ❌ Below 100% target
- **Test Coverage**: 3/3 requirements with tests (100%) ✅
- **Orphaned Requirements**: 1 (REQ-003: 2FA)
- **Orphaned Tests**: 1 (T-004: Session timeout)

## Gaps Identified

### Missing Implementation

- **REQ-003**: Two-factor authentication (no tasks, code, or tests)

### Orphaned Tests

- **T-004**: Session timeout test has no corresponding requirement

### Recommendations

1. Create requirement for session timeout or remove test
2. Implement REQ-003 (2FA) or defer to next release
3. Update traceability matrix after addressing gaps

Read the full file on GitHub · 404 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 404 lines · 173 tokens per session scan A dcd49585fa84

Subscribe to this mod's changes

traceability-auditor is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 173 tokens to every session and 3,032 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens