Skip to content
SkillModel-led7,248 tokens in use

bb-methodology

The orchestrator for a bug bounty session: confirm the engagement type, pick one goal, work through five non-linear phases and keep false positives out of the report.

14,517 stars on the repository MIT Licenseelementalsouls/Claude-BugHunter · skills/bb-methodology
/plugin marketplace add elementalsouls/Claude-BugHunter /plugin install claude-bughunter@elementalsouls
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing bb-methodology costs

90tokens idle
7,248tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectednetworkdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance84
  • Community68
  • Maturity28
  • Momentum40

bb-methodology is a skill for Claude Code meant to load at the start of a hunting session, when switching targets or when it is unclear what to do next. It combines a five-phase workflow (session start, recon, mapping, discovery, prove and validate) with a thinking framework built on developer psychology, anomaly spotting and what-if experiments.

It begins by asking which kind of engagement this is, such as a bug bounty, a red team, a pentest or an internal audit, because that decides what counts as a finding. It then routes to the other skills in the bundle by phase.

What You Get

  • A mode table that says what counts as a finding in a bounty, red team, pentest or audit
  • Five session goals to pick from: confidentiality, integrity, availability, account takeover or code execution
  • Four thinking domains with concrete what-if experiments
  • A five-phase flow with a 20-minute rotation clock and a tool-routing table by phase
  • Discipline rules on markers, response diffs, sample sizes and shell loops

Common Use Cases

  • Opening a hunt on a new target and deciding where to start
  • Recovering when a session stalls and the next step is unclear
  • Checking a timing-based claim before it goes into a report

What Makes It Unique

Many hunting guides list bug classes. This one organizes the person doing the hunt: it makes the engagement type explicit first, limits each session to one goal and one or two bug classes, and adds rules that catch false positives such as body diffs and statistical sampling for timing claims. It hands off to the class-specific skills by phase.

Under The Hood

The skill is a single SKILL.md of guidance with no scripts. It is mostly reasoning prompts, tables and routing notes, and it tells the agent to keep session notes in a file, so it may write notes to the working folder. It points to other skills for the commands that touch networks or tools, and it names tools by phase such as recon utilities and a proxy. Quoted examples of tampered requests appear as teaching text. Use it only on assets you are authorized to test.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers