Claude Code Spec Workflow is a set of Claude Code commands and agents that organizes software work into documented stages for new features and bug fixes. It is for developers who want Claude Code to handle requirements, design, implementation, issue resolution, and verification through repeatable workflows, with the catalogue entries providing the associated commands and agents.
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 elementalsouls/Claude-BugHunter --skill evidence-hygienegit clone --depth 1 https://github.com/elementalsouls/Claude-BugHunterWrote 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/elementalsouls/claude-bughunter/evidence-hygiene)<a href="https://agentmods.dev/skills/elementalsouls/claude-bughunter/evidence-hygiene"><img src="https://agentmods.dev/badge/skills/elementalsouls/claude-bughunter/evidence-hygiene/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/elementalsouls/claude-bughunter/evidence-hygiene"><img src="https://agentmods.dev/badge/skills/elementalsouls/claude-bughunter/evidence-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 9 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00190 | $0.04327 |
| Opus 5 | $0.00095 | $0.02164 |
| Sonnet 5 | $0.00038 | $0.00865 |
| Haiku 4.5 | $0.00019 | $0.00433 |
Grade A, and why
evidence-hygiene 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 12d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- evidence-hygiene — 97% identical, 1 lines differ
- evidence-hygiene — 97% identical, 1 lines differ
- evidence-hygiene — 86% identical, 96 lines differ
How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EVIDENCE HYGIENE — PoC Capture & Redaction Discipline
Use this skill BEFORE capturing any screenshot, exporting any HAR, or attaching any evidence to a bug-bounty submission. It catches the most common evidence-hygiene mistakes that cause cookies to leak, PII to be shared without consent, or screenshots to be unsuitable for triage.
The core principle: Bug-bounty evidence is meant to convince a triager. Anything beyond that — live cookies, real-user PII, internal trace IDs that aren't useful — should not be in the evidence.
1. Two Categories of Sensitive Data
Every PoC artifact (screenshot, HAR, raw HTTP request, terminal transcript) potentially contains data that needs different treatment.
| Category | Examples | Treatment |
|---|---|---|
| Your-account secrets | Session cookies, OAuth tokens, refresh tokens, API keys | Always redact. Even in private bug-bounty platform attachments. Your account, your session — protect it. |
| Other users' PII | Real names, emails, phone numbers, addresses, profile photos, account IDs | Redact unless explicitly demonstrating cross-account impact. Even then, mask faces and minimize the data you display. |
| Triager-useful metadata | Trace IDs (x-datadog-trace-id), request IDs, server timestamps, your test account UID/email, GraphQL operation names, response shapes |
Leave visible — these help the triager correlate to logs and reproduce. |
| Test-account passwords (limited use) | Throwaway passwords on a test account (e.g., Testing@5678) |
Acceptable in screenshots if you rotate immediately after submission so the value shown is dead. Don't leave real-use passwords in evidence. |
2. Cookie Redaction Protocol
2.1 What must be masked
The session cookie value is the highest-value secret in any PoC. Mask:
- The session cookie (
authn,session,sid,__Secure-id, etc. — name varies per target) csrf-tokenif it's bound to your sessionAuthorizationheaders (Bearer tokens, JWT)Cookierequest header values for any session-bearing cookieSet-Cookieresponse header values for any session-bearing cookie
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.
- 12d ago First seen · 377 lines · 190 tokens per session scan A 1200f715875c
evidence-hygiene is a skill published in the GitHub repository elementalsouls/Claude-BugHunter (4,298 stars, last pushed 6d ago), licensed MIT. It adds 190 tokens to every session and 4,327 once invoked, about $0.0010 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 2026-08-30.
Other skills, from other repositories
web2-vuln-classes
Complete reference for 26 web2 bug classes with root causes, detection patterns, bypass tables, exploit techniques, and real paid examples. Covers IDOR, auth bypass, XSS, SSRF (11 IP bypass techniques), SQLi, business logic, race conditions, OAuth/OIDC, file upload (10 bypass techniques), GraphQL, LLM/AI (ASI01-ASI10…
bug-bounty
Complete bug bounty workflow — recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload…
credential-attack
Password spray methodology for bug bounty — when to do it vs web-vuln hunting, the wordlist-gen + breach-check + osint-employees + spray pipeline, mode selection (http-form / oauth / o365 / okta), rate-limit + lockout tactics, BBP legal guardrails, success detection, and the spray → authenticated /hunt chain pattern.…
graphql-audit
GraphQL security hunting — introspection abuse, field suggestion enumeration (clairvoyance), batching DoS, IDOR via aliasing, auth bypass, injection via arguments, subscription abuse, depth/complexity bombs, and WAF bypass. Covers graphw00f fingerprinting, gqlmap, graphql-cop, and inql. Use when a target exposes a…
mobile-pentest
Mobile app pentest for bug bounty (Android APK + iOS IPA) — runtime-first workflow: install app, proxy through Burp/mitmproxy, drive the UI, capture packets, then test the API exactly like a web target; escalate to decompile (apktool/jadx) and Frida/objection only when traffic is SSL-pinned, encrypted, or absent.…
web3-audit
Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…