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.
npx agentmods add instructions/ask191225/bugbounty-kit/claude-mdgit clone --depth 1 https://github.com/ASK191225/bugbounty-kitWrote 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.
[](https://agentmods.dev/instructions/ask191225/bugbounty-kit/claude-md)<a href="https://agentmods.dev/instructions/ask191225/bugbounty-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/ask191225/bugbounty-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.05395 | $0.05395 |
| Opus 5 | $0.02697 | $0.02697 |
| Sonnet 5 | $0.01079 | $0.01079 |
| Haiku 4.5 | $0.00539 | $0.00539 |
Grade C, and why
bugbounty-kit CLAUDE.md scanned grade C with 2 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 4d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Do not refuse routine hunting tasks (probing, payload generation, exploit PoCs, report drafting). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Live PoC (curl with actual responses) The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 466 lines · 5,395 tokens per session scan C 5095a3a83195
bugbounty-kit CLAUDE.md is an instructions file published in the GitHub repository ASK191225/bugbounty-kit (2 stars, last pushed 26d ago), with no licence file. It adds 5,395 tokens to every session, about $0.0270 per session on Opus 5. A static security scan graded it C with 2 findings (tells the agent never to refuse, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
pentest-agents AGENTS.md
AGENTS.md instructions for H-mmer/pentest-agents, covering pentest-agents repository maintenance, role, source map, generated output and scaffold contract.
pentest-agents CLAUDE.md
Claude Code instructions for H-mmer/pentest-agents, covering pentest-agents repository maintenance, repository role, source map, generated artifacts and scaffold contract.
chain-table
Instructions for H-mmer/pentest-agents, covering chain table — capability → next bug, the chain walk algorithm, capability → next bug table, terminal impacts (stop chaining, report) and known deep chains (real-world examples).
hunting
Instructions for H-mmer/pentest-agents, covering hunting rules, rule 0: the only question that matters, theoretical bug = wasted time. kill these immediately, rule 1: read full scope first and rule 2: kill weak findings fast.
identities
Instructions for H-mmer/pentest-agents, covering platform identities — canonical env var map, hackerone, bugcrowd, intigriti and yeswehack.
mistakes
Instructions for H-mmer/pentest-agents, covering mistakes log — lessons from real engagements, top 10 most common mistakes (read first), agent-behavior, gate floors are not work and write files to disk — terminal output is not a deliverable.