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 skills add ShulkwiSEC/bb-huge --skill distill-skillgit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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/skills/shulkwisec/bb-huge/distill-skill)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/distill-skill"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/distill-skill/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.
<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/distill-skill"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/distill-skill.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00105 | $0.01367 |
| Opus 5 | $0.00053 | $0.00683 |
| Sonnet 5 | $0.00021 | $0.00273 |
| Haiku 4.5 | $0.00011 | $0.00137 |
Grade A, and why
distill-skill 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Distill Security Content to Skill
You are a knowledge distiller. Your job is to read raw security content — whatever form it comes in — and extract the reusable, transferable technique so another AI can use it to hunt the same class of vulnerability on a new target.
Repository Structure
Skills are organized by domain, then category:
skills/
meta/ ← skill generation and self-improvement tooling
distill-skill/
observe-skill/
amend-skill/
web/ ← web application security
recon/
auth/
session/
authz/
injection/
client-side/
logic/
mobile/ ← mobile security (Android + iOS)
storage/
crypto/
auth/
network/
platform/
code/
resilience/
cicd/ ← CI/CD pipeline security
Choose the right bucket:
web/— web application vulnerabilities (any source: OWASP WSTG, blog posts, CVEs, bug bounty)mobile/— mobile security (any source: OWASP MASTG, research, writeups)cicd/— CI/CD pipeline security (any source)meta/— skill tooling
Examples:
skills/web/injection/sql-injection/SKILL.md
skills/web/authz/bola-idor/SKILL.md
skills/mobile/storage/mobile-insecure-storage/SKILL.md
skills/mobile/crypto/mobile-weak-crypto/SKILL.md
skills/cicd/pwn-request/SKILL.md
skills/web/client-side/cspt/SKILL.md
Understanding the Source
Different sources carry different signal. Adapt your extraction focus accordingly:
- Bug report — mine for PoC mechanics, exact bypass, impact chain, payload
- Walkthrough / CTF writeup — focus on step ordering, tool choices, decision points, dead ends worth noting
- Pentest report — look for finding chains, lateral movement, misconfig patterns, what remediation they got wrong
- Blog post — extract the novel insight, the edge case, the researcher's mental model
- Ezine (Phrack, PoC||GTFO, etc.) — go deep on the primitive, the spec abuse, the creative leap
- Book chapter — pull out the taxonomy, the methodology scaffold, the conceptual model
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.
- 6d ago First seen · 153 lines · 105 tokens per session scan A a73e4745da4f
distill-skill is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 1,367 once invoked, about $0.0005 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.
Other skills, from other repositories
bugcrowd-reporting
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…
skill-context-detection
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type.
skill-copilot-provider
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode.
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
skill-security-framing
URL validation and content sanitization for untrusted sources — use when handling external input safely.
race
Race condition / TOCTOU playbook — limit overrun (one-time codes used twice, gift cards spent twice), single-packet attack (last-byte sync) to force parallel processing, and state-confusion races (file upload + read, order before payment). Use when timing-sensitive logic could be abused — one-time codes, coupons/gift…