patch-diff-research

patch-diff-research is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 26 tokens per session (514 once invoked), scanned A, original, Apache-2.0.

An authorized method for comparing vulnerable and fixed source-code versions to understand what security problem a patch addressed. It uses the change to look for related cases and tests both versions.

In plain words
What is it for?
Use it to review security patches, reproduce the original behavior, search for related code patterns, and validate candidate vulnerabilities.
Why use it?
It helps determine whether a fix covers the underlying weakness and whether similar issues remain nearby.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to review security patches, reproduce the original behavior, search for related code patterns, and validate candidate vulnerabilities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/patch-diff
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,463 stars · on GitHub · decepticon.red

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 PurpleAILAB/Decepticon --skill patch-diff
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

Made for: Claude Code.

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 patch-diff-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/patch-diff.svg)](https://agentmods.dev/skills/purpleailab/decepticon/patch-diff)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/patch-diff"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/patch-diff.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 514 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 $0.00026 $0.00514
Opus 5 $0.00013 $0.00257
Sonnet 5 $0.00005 $0.00103
Haiku 4.5 $0.00003 $0.00051

Measured 5d ago against content hash 89a02d8a1796, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

patch-diff-research 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.

packages/decepticon/decepticon/skills/standard/analyst/patch-diff/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Patch-Diff Research

Use this workflow only on source, commits, and test targets the engagement is authorized to inspect. A patch is evidence of a changed security boundary, not proof that every neighboring line is exploitable.

Inputs

  • Pinned vulnerable and fixed revisions from the same repository.
  • Build instructions and a local or intentionally vulnerable test target.
  • The advisory, failing test, or exact behavior corrected by the patch.

Loop

  1. Pin both sides. Record repository URL, vulnerable commit, fixed commit, clean working-tree state, dependency lockfile hashes, and build commands.
  2. Explain the security delta. Identify the source, guard, sink, trust boundary, and behavior changed by the patch. Ignore formatting-only hunks.
  3. Build a differential test. The positive case must reproduce on the vulnerable revision; the negative control is the exact same case on the fixed revision. Record both raw outputs.
  4. Search for siblings. Search only for the abstract cause—not the exact line text. For every hit, confirm framework, data flow, authorization state, and reachability before treating it as a candidate.
  5. Validate candidates independently. Each candidate gets its own minimal positive and baseline command through validate_workspace_finding. Do not inherit validation from the original CVE.
  6. Report the boundary. Record rejected siblings and why they differ. Group only independently confirmed findings under the common root cause.

Required artifacts

research/patch-diff/<advisory>/
  revisions.json                 # commits and dependency hashes
  security-delta.md              # source / guard / sink explanation
  original-positive.txt          # vulnerable revision output
  original-fixed-control.txt     # fixed revision output
  variants/<candidate>/positive.txt
  variants/<candidate>/baseline.txt
  variants/<candidate>/verification.json

A variant is promotable only when its own verification artifact validates and the original fixed-side control demonstrates the intended remediation boundary.

Read the full file on GitHub · 56 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 · 56 lines · 26 tokens per session scan A 89a02d8a1796

Subscribe to this mod's changes

patch-diff-research is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,463 stars, last pushed 9d ago), licensed Apache-2.0. It adds 26 tokens to every session and 514 once invoked, about $0.0001 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 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

A structured process for investigating and fixing software problems through four stages. It covers systematic debugging principles and rules.

xbsheng/atguigu-note · 24 tokens

nodejs-core

Debugs native module crashes, optimizes V8 performance, configures node-gyp builds, writes N-API/node-addon-api bindings, and diagnoses libuv event loop issues in Node.js. Use when working with C++ addons, native modules, binding.gyp, node-gyp errors, segfaults, memory leaks in native code, V8…

Harmeet10000/skills · 108 tokens

golang-error-handling

Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log…

Harmeet10000/skills · 94 tokens

nodejs-performave-with-flame

The agent possesses the ability to ingest, interpret, and act upon pprof-based Markdown analysis generated by tools like @platformatic/flame. It can bridge the gap between low-level CPU/Heap profiles and high-level architectural code fixes.

Harmeet10000/skills · 0 tokens

redteam-reverse-detail-pack

Domain routing and boundary guidance for authorized reverse engineering analysis, including decompilation, debugging, protocol reversing, firmware extraction, and deobfuscation. Use when a task belongs to the reverse engineering domain and needs scope, evidence, pivot, or exit criteria.

Unclecheng-li/DeepSec · 59 tokens

memory-safety-patterns

Implement memory-safe programming with RAII, ownership, smart pointers, and resource management across Rust, C++, and C. Use when writing safe systems code, managing resources, or preventing memory bugs.

Harmeet10000/skills · 45 tokens