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 agentmods add commands/elementalsouls/claude-bughunter/reportgit 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/commands/elementalsouls/claude-bughunter/report)<a href="https://agentmods.dev/commands/elementalsouls/claude-bughunter/report"><img src="https://agentmods.dev/badge/commands/elementalsouls/claude-bughunter/report.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 5.1 | $0.00054 | $0.00930 |
| Opus 5 | $0.00027 | $0.00465 |
| Sonnet 5 | $0.00011 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
report 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.
This is a copy
86% identical to report — 23 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/report
Generate a submission-ready bug bounty report.
Pre-Conditions
Run /validate first. All 4 gates must pass before running this command.
Never write a report before validating. N/A submissions hurt your validity ratio.
Usage
/report
Provide when prompted:
- Platform (HackerOne / Bugcrowd / Intigriti / Immunefi)
- Bug class
- Affected endpoint
- Your two test accounts and their IDs
- The exact HTTP request that demonstrates the bug
- The exact response that shows the impact
- Tech stack (for CVSS and remediation advice)
What This Generates
- Title following the formula:
[Bug Class] in [Endpoint] allows [actor] to [impact] - Summary paragraph (impact-first, no "could potentially")
- Vulnerability details with CVSS 3.1 score and vector string
- Steps to Reproduce with copy-paste HTTP requests
- Impact statement with quantification
- Recommended fix (1-2 sentences, specific)
- Supporting materials section
Platform Selection
HackerOne Format
- Markdown sections: Summary, Vulnerability Details, Steps to Reproduce, Impact, Recommended Fix
- Include CVSS 3.1 score + vector string
- Include two test account setup instructions
- Keep under 600 words
Bugcrowd Format
- Title with VRT category:
[VRT Category] > [Subcategory] > P[1-4] - Expected vs Actual Behavior section
- Severity Justification section referencing Bugcrowd VRT
Intigriti Format
- CVSS score prominent at top
- Clear reproduction steps
- Business impact focused
Immunefi Format (Web3)
- Root cause in Solidity code
- Foundry PoC test included
- Economic impact quantified in $ value
- Comparison evidence (same check present elsewhere, missing here)
Writing Rules
- Never use: "could potentially", "may allow", "might be possible"
- Always prove: show actual data/action, not just "200 OK"
- Impact first: sentence 1 = what attacker gets, not what the bug is
- Quantify: how many users affected, what data type, $ amount
- Short: triagers skim. < 600 words.
- Human: write to a person, not a system
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 · 117 lines · 0 tokens per session scan A e23eafa39e09
report is a command published in the GitHub repository elementalsouls/Claude-BugHunter (4,298 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 930 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to report, differing in 23 lines, and is treated as a copy.
Other commands, from other repositories
bypass-403
Probe a 403/401 endpoint with the most-paid bypass tricks (header injection, path encoding, method swap, WAF fingerprint, vendor-specific). Wraps byp4xx when installed; otherwise runs a built-in matrix of 38+ techniques. Usage: /bypass-403 | /bypass-403 -l.
spray
Password spray with hard guards — typed-hostname confirmation, lockout warning, audit log. Modes: http-form (custom login page), oauth (password grant), o365 + okta (via TREVORspray). Default delay 30min/round + 60s jitter. Usage /spray --mode --users --passes.
web3-audit
Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage…
autopilot
Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].
recon
Run the full recon pipeline by invoking tools/reconengine.sh — subdomain enum (subfinder + amass + crt.sh + wayback), httpx live host probing with tech detection, nmap port scan, gau URL collection, JS analysis, ffuf directory fuzzing, parameter discovery, config exposure check, CI/CD workflow scan. Outputs to recon/…
report
Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report.