pdqc

pdqc is a command for Claude Code from mumerfarooq-con/asdlc-tools. It costs 41 tokens per session (870 once invoked), scanned A, original, MIT.

A pre-delivery check for an almost-finished codebase that examines the assembled application rather than only one change or pull request.

In plain words
What is it for?
Use it before shipping to find issues across the whole project and delegate required fixes. It reports findings but does not edit code itself.
Why use it?
It catches cross-cutting inconsistencies, missing documentation, weak error handling, maintenance problems, and production-readiness gaps that smaller reviews can miss.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the asdlc plugin — 3 commands, 15 agents shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add mumerfarooq-con/asdlc-tools
Claude Code
/plugin install asdlc

Made for: Claude Code.

Or install asdlc, the plugin that ships this one along with the rest of its 3 commands, 15 agents.

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 pdqc

README.md
[![agentmods](https://agentmods.dev/badge/commands/mumerfarooq-con/asdlc-tools/pdqc.svg)](https://agentmods.dev/commands/mumerfarooq-con/asdlc-tools/pdqc)
Your own site
<a href="https://agentmods.dev/commands/mumerfarooq-con/asdlc-tools/pdqc"><img src="https://agentmods.dev/badge/commands/mumerfarooq-con/asdlc-tools/pdqc.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 870 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 5.1 $0.00041 $0.00870
Opus 5 $0.00020 $0.00435
Sonnet 5 $0.00008 $0.00174
Haiku 4.5 $0.00004 $0.00087

Measured 5d ago against content hash 553f5264db6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pdqc 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 5d 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.

plugins/asdlc/commands/pdqc.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pdqc — Pre-Delivery Quality Check

Run this once on a codebase approaching delivery. It catches the class of issues per-PR review cannot see because they only exist in the assembled whole: cross-cutting inconsistency, documentation gaps, maintainability and debt, error/edge coverage, and production readiness.

Hard constraint (inherited from the PR Reviewer): PDQC never modifies code. It produces findings and delegates required changes to the PRD Implementor.

Phase 0 — Discovery and context assembly

  1. Run the discovery contract (${CLAUDE_PLUGIN_ROOT}/pdqc/discovery/discovery.md). Locate the repo's standards docs, architecture docs, and any existing sub-agent/command definitions. If discovery is not yet trusted, load the explicit fallback config (${CLAUDE_PLUGIN_ROOT}/pdqc/discovery/pdqc.config.example.yaml) — do not debug discovery and detection at the same time.
  2. Select the stack profile from ${CLAUDE_PLUGIN_ROOT}/pdqc/profiles/ (django, fastapi, node-express, react) by the repo's dominant framework; a repo may warrant more than one (e.g. a React frontend with an Express API). If none matches, proceed with convention-derivation only and note the gap.
  3. Build the codebase map: every route with method/params/response shape; the module/layer graph; the set of error types and where raised; data models; the config surface; external dependencies. This is the shared context all inspectors read.
  4. Calibration (optional). If use_seed_checklist: true and a seed checklist exists, load it from the seed_checklist path in the target repo's pdqc.config.yaml (the plugin does not ship one — generate it with ${CLAUDE_PLUGIN_ROOT}/pdqc/calibration/extract_seed_checklist.py; format sample: ${CLAUDE_PLUGIN_ROOT}/pdqc/calibration/seed-checklist.sample.md); its checks run first and are tagged source: seed_checklist. If it is absent or disabled — the default for any codebase without usable ticket history — run in blind mode: the inspectors apply their charters uniformly with no project-specific prioritization. Blind mode is fully supported and is the expected path for a fresh codebase; the seed only sharpens where inspectors look first, never what they are able to find.

Read the full file on GitHub · 42 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. 5d ago First seen · 42 lines · 41 tokens per session scan A 553f5264db6b

Subscribe to this mod's changes

pdqc is a command published in the GitHub repository mumerfarooq-con/asdlc-tools (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 870 once invoked, about $0.0002 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.