pqc-scan

pqc-scan is a skill for Claude Code from StanimirTenev/qrp-mcp. It costs 50 tokens per session (851 once invoked), scanned A, original, Apache-2.0.

A code-scanning workflow that inventories cryptographic algorithms a quantum computer could break and records files it could not read.

In plain words
What is it for?
Use it to scan a codebase, classify algorithms, report their file and line locations, and identify missing scan coverage.
Why use it?
It shows where vulnerable or uncertain cryptography appears in a project, which helps assess post-quantum readiness.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the qrp plugin — 1 skill, 1 MCP server shipped together

Good fit Use it to scan a codebase, classify algorithms, report their file and line locations, and identify missing scan coverage.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stanimirtenev/qrp-mcp/pqc-scan
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 StanimirTenev/qrp-mcp --skill pqc-scan
Clone the repo
git clone --depth 1 https://github.com/StanimirTenev/qrp-mcp

Made for: Claude Code.

Or install qrp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 pqc-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/stanimirtenev/qrp-mcp/pqc-scan/github.svg)](https://agentmods.dev/skills/stanimirtenev/qrp-mcp/pqc-scan)
Your own site
<a href="https://agentmods.dev/skills/stanimirtenev/qrp-mcp/pqc-scan"><img src="https://agentmods.dev/badge/skills/stanimirtenev/qrp-mcp/pqc-scan/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 pqc-scan

Your own site · 80×15
<a href="https://agentmods.dev/skills/stanimirtenev/qrp-mcp/pqc-scan"><img src="https://agentmods.dev/badge/skills/stanimirtenev/qrp-mcp/pqc-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 851 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 $0.00050 $0.00851
Opus 5 $0.00025 $0.00426
Sonnet 5 $0.00010 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 7d ago against content hash 49d516c94994, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pqc-scan 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 7d 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.

plugin/skills/pqc-scan/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cryptographic inventory

Scan the directory the user names with the scan_repo tool from the qrp MCP server. If they name none, scan the current working directory.

Report in this order.

1. What was found. Each algorithm, its classification — quantum-vulnerable, post-quantum, weak, or unknown — with the file and line, so the user can open it. For post-quantum schemes, give the family it rests on (structured or unstructured lattice, code-based, hash-based, isogeny-based, multivariate, symmetric-based) and where it stands: standardised, selected, candidate, withdrawn, eliminated, or broken. "Post-quantum" is a category, not an assessment: SIKE is broken, HAWK was withdrawn by its own authors, and CROSS was dropped by NIST — all three are post-quantum by design.

Report also_present whenever it is set. A hybrid or composite name carries two algorithms: X25519MLKEM768 is ML-KEM and X25519, and id-MLDSA44-RSA2048-PSS-SHA256 is ML-DSA and RSA-2048. The construction holds if either half holds, which is why the post-quantum name leads — but the classical half is the component Shor breaks, and a summary that names only the post-quantum one is describing the half that is fine. Say both.

2. What the scan could not read. State unreadable_files and its count plainly, even when it is zero. A file nobody could open is not a file that is clean, and the difference is the coverage of the whole report. Never let an unreadable file pass as an absence of findings.

3. Coverage, as a fraction with a real base. files_scanned against files_present — how much was read, out of how much was there. Then files_skipped_by_type: files not read because this tool does not claim that type, counted by extension. That is a boundary of the scan, not a gap in it, but it is the reader's to judge, not yours to hide. The three outcomes always account for every file: scanned, unreadable, skipped.

If the skipped list contains something that could hold cryptography — .env, .pem, .p12, .json, a Dockerfile, a binary — say so, and offer to look at those files yourself. You are holding the tree; the scanner is not. That question is the one thing you can answer that it cannot.

Then stop.

Read the full file on GitHub · 61 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. 7d ago First seen · 61 lines · 50 tokens per session scan A 49d516c94994

Subscribe to this mod's changes

pqc-scan is a skill published in the GitHub repository StanimirTenev/qrp-mcp (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 851 once invoked, about $0.0003 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 2026-09-04.