secagent-methodology

secagent-methodology is a skill for Claude Code, Codex from JesusConwellpy/secagent-skills. It costs 39 tokens per session (1,193 once invoked), scanned A, original, MIT.

A step-by-step security testing method covering reconnaissance, finding weaknesses, verifying them, and reporting evidence. It adapts the workflow to tasks such as CTF challenges, penetration tests, code audits, and binary analysis.

In plain words
What is it for?
It is for examining web targets, source code, compiled programs, and known vulnerabilities during authorized security research.
Why use it?
It gives security work a consistent process and helps avoid making decisions without checking the evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for examining web targets, source code, compiled programs, and known vulnerabilities during authorized security research.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jesusconwellpy/secagent-skills/secagent-methodology
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 JesusConwellpy/secagent-skills --skill secagent-methodology
Clone the repo
git clone --depth 1 https://github.com/JesusConwellpy/secagent-skills

Made for: Claude Code, Codex.

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 secagent-methodology

README.md
[![agentmods](https://agentmods.dev/badge/skills/jesusconwellpy/secagent-skills/secagent-methodology/github.svg)](https://agentmods.dev/skills/jesusconwellpy/secagent-skills/secagent-methodology)
Your own site
<a href="https://agentmods.dev/skills/jesusconwellpy/secagent-skills/secagent-methodology"><img src="https://agentmods.dev/badge/skills/jesusconwellpy/secagent-skills/secagent-methodology/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 secagent-methodology

Your own site · 80×15
<a href="https://agentmods.dev/skills/jesusconwellpy/secagent-skills/secagent-methodology"><img src="https://agentmods.dev/badge/skills/jesusconwellpy/secagent-skills/secagent-methodology.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00039 $0.01193
Opus 5 $0.00019 $0.00596
Sonnet 5 $0.00008 $0.00239
Haiku 4.5 $0.00004 $0.00119

Measured 9d ago against content hash 6b931e42359e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

secagent-methodology scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Web: curl -s <url> | head -100; curl -s -I <url>
secagent-methodology/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SecAgent Methodology

Loading this SKILL gives you a universal security workflow. It adapts to any task type.

Task Classification (First step)

Classify before acting:

1. CTF challenge?
   → Solo execution. Analyze challenge directly. No agent spawn.
   → Key: read source → identify all checkpoints → bypass each one

2. Pentest (multi-target/multi-service)?
   → Use agents. Spawn in parallel. Full Phase 1-4.

3. Code audit?
   → Solo. Read file by file → trace data flow → mark vulnerability points.

4. Binary analysis?
   → Solo. checksec → disassemble → find vuln → write exploit.

5. CVE research?
   → Solo. Search → match → verify.

Phase 1: RECON — Know your target

1. Gather basic info:
   - Web: curl -s <url> | head -100; curl -s -I <url>
   - Binary: file <binary>; checksec <binary>; strings <binary>
   - Code: read entry file → trace includes → read all related files

2. Identify tech stack:
   - Language, framework, version
   - Entry points (URL params, API endpoints, file inputs)
   - Security mechanisms (WAF, auth, input validation)

3. If CTF:
   - Read complete source
   - List all inputs: GET/POST params, headers, cookies, file uploads
   - List all checkpoints: if/die statements, preg_match, filter_var, escapes

Phase 2: ANALYZE — From observation to hypothesis

1. Map data flow:
   Input → Validation/Filter → Processing → Output
   At each step: who controls the data? what constraints exist?

2. Identify vulnerability categories:
   Web:     SQLi, XSS, RCE, LFI, SSRF, CSRF, IDOR, SSTI, File Upload
   Binary:  BOF, Format String, UAF, Integer Overflow, Race Condition
   Crypto:  Weak cipher, Padding Oracle, Hash extension, Nonce reuse
   General: Auth bypass, PrivEsc, Info disclosure, Logic flaw

3. For each checkpoint, ask:
   - What does it check? (type, length, format, range, origin)
   - Bypass method? (type juggling, encoding, null byte, overflow, race)
   - Is this checkpoint unnecessary? (alternative path? later code overwrites it?)

4. Identify red herrings:
   - Computationally infeasible checks (hash preimage, collision)
   - Dead code (after die())
   - Variables overwritten by later steps

5. Form hypotheses: testable, falsifiable. Give confidence 0-1.

Read the full file on GitHub · 148 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. 9d ago First seen · 148 lines · 39 tokens per session scan A 6b931e42359e

Subscribe to this mod's changes

secagent-methodology is a skill published in the GitHub repository JesusConwellpy/secagent-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,193 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

osint-recon

A knowledge guide for open-source intelligence, or OSINT: collecting information from publicly available sources. It covers servers, websites, domains, and, when appropriate, people.

Netw0rkNoob/VulnClaw · 42 tokens

secknowledge-skill

A knowledge base for testing the security of websites, software, and AI systems, including agents and language models.

Netw0rkNoob/VulnClaw · 321 tokens

performing-ai-assisted-vulnerability-discovery

Using LLMs to accelerate vulnerability research and pentest workflows — generating syntax-valid fuzzing seeds and evolving grammars, fine-tuned mutation dictionaries, parallel agent-based proof-of-vulnerability generation, and evidence-driven passive analysis of real HTTP traffic via the Burp MCP server. Covers…

xalgorix/xalgorix · 91 tokens

client-reverse

A workflow for analysing and replaying requests made by mobile apps, browser JavaScript, or desktop clients during authorised security testing.

Netw0rkNoob/VulnClaw · 56 tokens

redteam-crypto-detail-pack

Domain routing and boundary guidance for authorized cryptography weakness testing, including weak algorithms, padding oracles, key management errors, insecure randomness, and hash collision risks. Use when a task belongs to the cryptography testing domain and needs scope, evidence, pivot, or exit criteria.

Netw0rkNoob/VulnClaw · 62 tokens

redteam-logic-detail-pack

Domain routing and boundary guidance for authorized business logic vulnerability testing, including race conditions, flow bypass, price tampering, permission logic errors, and bulk operation abuse. Use when a task belongs to the logic testing domain and needs scope, evidence, pivot, or exit criteria.

Netw0rkNoob/VulnClaw · 61 tokens