agentmods.dev

mcp-requirements-traceability

mcp-requirements-traceability is a skill for Claude Code, Codex from sharpninja/McpServer. It costs 89 tokens per session (2,255 once invoked), scanned A, original, Apache-2.0.

A requirements-tracking assistant for MCP servers. It manages functional, technical, and test requirements, plus links showing how each functional requirement is implemented and tested.

In plain words
What is it for?
Use it to add, edit, map, audit, or regenerate MCP requirements and to fix traceability validation failures.
Why use it?
It helps find missing implementation or test coverage and keeps the requirements database, documentation, and validation checks consistent.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

not rated 4repo changed 4d ago A scan 89 tokens original Apache-2.0

Good fit Use it to add, edit, map, audit, or regenerate MCP requirements and to fix traceability validation failures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sharpninja/mcpserver/mcp-requirements-traceability
View source ↗ sharpninja/McpServer sharpninja.github.io
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.

Any agent
npx skills add sharpninja/McpServer --skill mcp-requirements-traceability
Clone the repo
git clone --depth 1 https://github.com/sharpninja/McpServer

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-requirements-traceability

README.md
[![agentmods](https://agentmods.dev/badge/skills/sharpninja/mcpserver/mcp-requirements-traceability/github.svg)](https://agentmods.dev/skills/sharpninja/mcpserver/mcp-requirements-traceability)
Your own site
<a href="https://agentmods.dev/skills/sharpninja/mcpserver/mcp-requirements-traceability"><img src="https://agentmods.dev/badge/skills/sharpninja/mcpserver/mcp-requirements-traceability/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-requirements-traceability

Your own site · 80×15
<a href="https://agentmods.dev/skills/sharpninja/mcpserver/mcp-requirements-traceability"><img src="https://agentmods.dev/badge/skills/sharpninja/mcpserver/mcp-requirements-traceability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,255 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00089 $0.02255
Opus 5.5 $0.00036 $0.00902
Sonnet 5.5 $0.00018 $0.00451
Haiku 4.5 $0.00009 $0.00226

Measured 4d ago against content hash aa0e8b634c70, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-requirements-traceability 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 4d 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.

skills/mcp-requirements-traceability/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Requirements Traceability

Manage QBrain.AI functional (FR), technical (TR), and test (TEST) requirements, their FR -> TR/TEST mappings, and structured acceptance criteria. The requirements database is the source of truth; the Markdown files under docs/Project/ are import/export projections that ./build.ps1 ValidateTraceability reads. Keep both in sync so the build stays green.

When to Use

  • Adding or editing FR / TR / TEST records, or their acceptance criteria.
  • Linking an FR to its TRs and TESTs (the traceability mapping).
  • Fixing a failing ./build.ps1 ValidateTraceability run.
  • Auditing coverage (which FR lacks a TR or a TEST).
  • Regenerating the requirements Markdown / wiki projections from the database.

When Not to Use

  • Managing TODO items or session logs: use the todo and session skills instead. Requirement IDs are distinct from TODO IDs (PLAN-AREA-###) and Session IDs.
  • Editing the requirement Markdown files in docs/Project/ by hand. Never hand-edit Functional-Requirements.md, Technical-Requirements.md, Testing-Requirements.md, TR-per-FR-Mapping.md, or Requirements-Matrix.md. Mutate records through the plugin and regenerate the docs.

Inputs

  • The workspace marker / API key from AGENTS-README-FIRST.yaml (read once per session).
  • A requirement area (and subarea for TR), plus title, description, priority.
  • For mappings: an frId and the trIds / testIds to link.
  • For validation: the five Markdown files under F:\GitHub\QBrainAi\docs\Project\.

Critical Rules

  • The database is authoritative. Markdown under docs/Project/ is a generated projection. After mutating records, regenerate the docs with workflow.requirements.generateDocument so the IDs land in the files the validator scans. Do NOT hand-edit those files.
  • ID grammar (uppercase, validated server-side):
    • FR: FR-<AREA>-### (e.g. FR-MCP-001). Area segment only.
    • TR: TR-<AREA>-<SUBAREA>-### (e.g. TR-MCP-ARCH-001). Both area and subarea required.
    • TEST: TEST-<AREA>-### (e.g. TEST-MCP-001). Area segment only.
  • Coverage rule the validator and CI enforce: every FR should map to at least one TR and at least one TEST, and every FR/TR/TEST ID must be present in the matrix.
  • All requirements work goes through the plugin workflow.requirements.* namespace (the Claude Code plugin wrapper, surfaced over REPL YAML/STDIO). Do not substitute raw REST or another agent's plugin for normal requirements work.
  • Capture requirements as they emerge during a session; do not defer. Record the new IDs in the session log turn tags.

Read the full file on GitHub · 149 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. 4d ago Changed · +2 tokens per session aa0e8b634c70
  2. 1mo ago First seen · 149 lines · 87 tokens per session scan A a91aab94c720

Subscribe to this mod's changes

mcp-requirements-traceability is a skill published in the GitHub repository sharpninja/McpServer (4 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 2,255 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.

PlanningTestingai-agentsai-mcpai-tools
Related

Other skills, from other repositories

omh-agent-evaluation

This is a Hermes-native agent-evaluation workflow skill.

rlaope/oh-my-hermes · 71 tokens

omh-verification-gate

This is an OMH verification-gate workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 79 tokens

debugging

Use this skill when something is broken and the cause is unknown — a failing test, a crash, an error message, wrong output, a regression, a hang, or behaviour that differs between environments — and it has to be found and fixed at the root. Also use it to build the failing proof for a suspected defect before fixing…

WrongStack/WrongStack · 148 tokens

visual-regression

Setup visual regression testing with Storybook stories, configuration, and CI/CD workflows. Supports Chromatic, Percy, BackstopJS. Auto-invoke when user says "set up visual regression", "add Chromatic tests", "add screenshot testing", or "set up Percy".

qf-studio/navigator · 59 tokens

Vizra ADK Evaluation Framework

Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.

vizra-ai/vizra-adk · 26 tokens

agent-e2e-test-specialist

Specialist subagent: Playwright, Cypress, and visual regression testing specialist. Use only when the user explicitly asks for E2E tests, browser test automation, or visual regression testing. Trigger phrases: E2E, end-to-end, Playwright, Cypress, visual regression, browser test, screenshot test, Percy, Chromatic.

travisjneuman/.claude · 76 tokens