tt-workflow-audit

tt-workflow-audit is a skill for Claude Code from mhylle/claude-skills-collection. It costs 302 tokens per session (3,022 once invoked), scanned A, original, MIT.

A project-wide audit tool that splits a code repository, task backlog, or system design into sections and has separate read-only agents inspect each one. It combines their checked findings into a ranked list of risks.

In plain words
What is it for?
Use it to find bugs, design risks, missing work, and other problems across a repository, backlog, or architecture. It is suited to broad audits where several independent areas can be reviewed at once.
Why use it?
It reduces the time and effort needed to review a large project, while avoiding duplicate findings. Only the main session changes tasks, so parallel reviews do not interfere with each other.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; mentions Claude Code.

Part of the devflow plugin — 38 skills, 13 agents, 5 hooks shipped together

Good fit Use it to find bugs, design risks, missing work, and other problems across a repository, backlog, or architecture. It is suited to broad audits where several independent areas can be reviewed at once.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mhylle/claude-skills-collection/tt-workflow-audit
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 mhylle/claude-skills-collection --skill tt-workflow-audit
Clone the repo
git clone --depth 1 https://github.com/mhylle/claude-skills-collection

Made for: Claude Code.

Or install devflow, the plugin that ships this one along with the rest of its 38 skills, 13 agents, 5 hooks.

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 tt-workflow-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/tt-workflow-audit/github.svg)](https://agentmods.dev/skills/mhylle/claude-skills-collection/tt-workflow-audit)
Your own site
<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/tt-workflow-audit"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/tt-workflow-audit/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 tt-workflow-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/tt-workflow-audit"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/tt-workflow-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 302 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,022 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00302 $0.03022
Opus 5 $0.00151 $0.01511
Sonnet 5 $0.00060 $0.00604
Haiku 4.5 $0.00030 $0.00302

Measured 11d ago against content hash 2f0ba58c593c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tt-workflow-audit 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 11d 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/tt-workflow-audit/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tt-workflow-audit

A tasktracker-native, Workflow-tool-backed project-wide audit. It is the first concrete skill in the tt-workflow-* tier — the "parallel and tasktracker-correct" quadrant that neither the sequential tt-* skills nor the tasktracker-blind team-* skills covered.

The shape is a hybrid: the parent (this session) scouts and partitions inline, fans the analysis out through one Workflow run, then does all writes in the tail. The parallel agents only read and report.

CRITICAL: the contract is non-negotiable

Read references/workflow-tasktracker-contract.md before running. It is the shared contract for every tt-workflow-* skill, grounded in verified facts about the live system.

The one rule you cannot break:

The Workflow SCRIPT orchestrates.
Parallel agent() calls are READ/ANALYZE-ONLY and return schema output.
The PARENT (this main-loop session) performs ALL tasktracker writes — serially.

Why (verified): the active task is a single process-global pointer, parallel workflow agents share one session id + one MCP process, and the shared stdio MCP cannot attribute a tool call to a specific agent. So no agent may call setActiveTask or any write-gated tool — it would clobber the shared pointer and bill time to the wrong task. Reads are fine (gate-exempt and reachable in background runs, probe-verified).

DO (parent) DON'T
Read project-invariant context once, pass it down Let agents re-fetch the same context N×
Partition the audit scope Let agents call setActiveTask
Fan out read-only agents via Workflow Let agents call logDefect/updateTaskStatus/batchCreate*
Aggregate findings → risk register Edit a locked phase body
Write fixes back in the tail (with an active task set) Write back destructively without a dry-run + confirmation

How this differs from the other audit skills

/code-quality-audit /codebase-audit, /adversarial-reviewer --codebase /tt-workflow-audit (this)
Engine metrics tools sequential / small Task fan-out Workflow tool — deterministic parallel fan-out, journaled, resumable
Output metrics report written report / risk register schema-checked risk register + optional tasktracker tasks
Tasktracker none none native — write-back as Bug-Fix-phase tasks, insight logging, all parent-owned
Resumes after crash/rate-limit no no yes (completed partitions cached)

Read the full file on GitHub · 200 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 200 lines · 302 tokens per session scan A 2f0ba58c593c

Subscribe to this mod's changes

tt-workflow-audit is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 8d ago), licensed MIT. It adds 302 tokens to every session and 3,022 once invoked, about $0.0015 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.