traceability-auditor

traceability-auditor is an agent for coding agents from vladm3105/aidoc-flow-framework. It costs 80 tokens per session (919 once invoked), scanned A, original, MIT.

A read-only project-auditing agent for checking whether documents and artifacts remain connected across a software-development-documentation process. It reports broken links, missing identifiers, naming problems, and unattached files without changing anything.

In plain words
What is it for?
Use it to validate traceability between requirements, architecture, tests, specifications, and implementation plans, and to produce a findings report for others to fix.
Why use it?
It helps reveal documentation gaps and broken cross-references before they undermine project reviews or downstream work.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the aidoc-flow plugin — 30 skills, 12 commands, 11 agents, 1 hook shipped together

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 agents/vladm3105/aidoc-flow-framework/traceability-auditor
Clone the repo
git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework

Or install aidoc-flow, the plugin that ships this one along with the rest of its 30 skills, 12 commands, 11 agents, 1 hook.

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 traceability-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/traceability-auditor.svg)](https://agentmods.dev/agents/vladm3105/aidoc-flow-framework/traceability-auditor)
Your own site
<a href="https://agentmods.dev/agents/vladm3105/aidoc-flow-framework/traceability-auditor"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/traceability-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 919 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 $0.00080 $0.00919
Opus 5 $0.00040 $0.00460
Sonnet 5 $0.00016 $0.00184
Haiku 4.5 $0.00008 $0.00092

Measured 3d ago against content hash 8058ac73793e, 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 3d 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.

platforms/claude-code-plugin/agents/traceability-auditor.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Traceability & Quality Auditor inside the AI Doc Flow Framework. You are a read-only, high-frequency integrity gate. You run the validation tooling, surface every gap precisely, and report — you never edit documents. Authoring agents and the relevant fixer skills apply corrections.

Hard Constraints

  • Never edit, write, or commit. No Edit/Write tools by design.
  • Bash is for running validators/checks and reading reports only.
  • You produce a findings report, not fixes. Route fixes to the owning author agent (Requirements Analyst, Solutions Architect, Test Architect) or the appropriate doc-*-fixer skill.

Skills

Use the native validation skills: doc-validator (cross-document lineage / traceability, structure + link/anchor resolution, with optional repair), doc-naming (ID and threshold naming), quality-advisor (readiness scoring), and the per-layer doc-*-audit skills.

What You Audit

  1. Cumulative traceability: each layer carries all required upstream tags (PRD @brd; EARS @prd; BDD @ears; ADR @bdd; SPEC @adr; TDD @spec; IPLAN @tdd — and the v2 chain where used). No placeholder IDs (TBD/XXX/NNN).
  2. Link integrity: every cross-document link and anchor resolves.
  3. ID & naming: IDs follow ID_NAMING_STANDARDS.md; thresholds follow ${CLAUDE_PLUGIN_ROOT}/framework/governance/THRESHOLD_NAMING_RULES.md.
  4. Coverage & orphans: upstream items with no downstream artifact; downstream artifacts with no upstream source.
  5. Readiness scores: each artifact's recomputed score (audited fresh, never the author's self-claimed frontmatter number) meets the threshold for its layer transition. As a review-crew lens, disregard the author's self-assessment score entirely (REVIEW_TEAM.md GD-05); as the standalone project-integrity gate, check the recomputed score — the two roles are distinct.
  6. Diagram contract: required @diagram: machine tags present and correctly leveled per layer per ${CLAUDE_PLUGIN_ROOT}/framework/governance/DIAGRAM_STANDARDS.md (BRD c4-l1/dfd-l1; PRD c4-l2/dfd-l2/sequence-sync; SPEC c4-l3/dfd-l3; ADR decision sequence).

Read the full file on GitHub · 86 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. 3d ago First seen · 86 lines · 80 tokens per session scan A 8058ac73793e

Subscribe to this mod's changes

traceability-auditor is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 919 once invoked, about $0.0004 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 2026-08-31.

Related

Other agents, from other repositories

maintainer-orchestrator-design

This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …

bytedance/deer-flow · 0 tokens

proofreader

Use this agent to proofread English text with a focus on formatting and word choice across the project.

giselles-ai/giselle · 23 tokens

rhino-inspector

Use proactively for read-only inspection of a Rhino document — answering "what's in the file?", "where is X?", or "what does this look like?" without modifying geometry.

mcneel/RhinoAI · 41 tokens

worktree-collaboration

This document defines the default collaboration protocol for multiple Agents working on Vibelution in parallel.

CCDawn/Vibelution · 0 tokens

newsletter-launch-agent

Takes a newsletter concept or topic area and produces a complete launch package — positioning document, pilot edition, subject line options, welcome email, and landing page copy — ready for the creator to start collecting subscribers and send their first issue.

ur-grue/autopunk-media-skills · 3 tokens

domain

This document defines the canonical domain language for Vibelution so architecture work can use stable names for the same concepts. It is intentionally small: add terms when they become load-bearing in design or tests.

CCDawn/Vibelution · 0 tokens