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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/elementalsouls/Claude-BugHunternpx agentmods add commands/elementalsouls/claude-bughunter/surfaceWrote 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/surface)<a href="https://agentmods.dev/commands/elementalsouls/claude-bughunter/surface"><img src="https://agentmods.dev/badge/commands/elementalsouls/claude-bughunter/surface/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/commands/elementalsouls/claude-bughunter/surface"><img src="https://agentmods.dev/badge/commands/elementalsouls/claude-bughunter/surface.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 | $0.00051 | $0.00458 |
| Opus 5.5 | $0.00020 | $0.00183 |
| Sonnet 5.5 | $0.00010 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
surface 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 1mo 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
1 near-identical copy found in the catalogue:
- surface — 100% identical, 0 lines differ
What it actually says
/surface
View the prioritized attack surface for a target.
What This Does
- Reads the recon manifest at
recon/<target>/manifest.json(produced bycbh recon) — the deterministic ranking comes fromcbh surface <target> - Reads hunt memory for patterns and previously tested endpoints
- Layers
engine/skill_map.py(surface → bug-class → skill) + ledger signal on top of the manifest'sranked_surface(P1/P2/Kill) - Outputs P1 (start here), P2 (after P1), and Kill List (skip)
The manifest is the recon→hunt contract — see
docs/recon-manifest.md. Runcbh surface <target>for the raw deterministic ranking.
Usage
/surface target.com
Prerequisites
Run /recon target.com first. If no recon data exists, you'll be prompted to run recon.
Output
ATTACK SURFACE: target.com
═══════════════════════════════════════
Priority 1 (start here):
1. api.target.com/v2/users/{id} — IDOR candidate
Tech: Express + PostgreSQL | First seen 12 days ago
Suggested: numeric ID swap on GET/PUT/DELETE
2. api.target.com/graphql — introspection enabled, 47 mutations
Suggested: field-level auth check on sensitive mutations
Priority 2 (after P1):
1. cdn.target.com:8443/upload — file upload endpoint
Suggested: extension bypass, magic bytes
Kill List (skip):
- static.target.com — CDN only
- docs.target.com — third-party hosted
Memory:
- Pattern from alpha.com (same tech): auth bypass via method override ($800)
- 3 endpoints tested in previous session, 5 remain
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.
- 1mo ago First seen · 58 lines · 0 tokens per session scan A b0af55c13783
surface is a command published in the GitHub repository elementalsouls/Claude-BugHunter (5,150 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 458 once invoked, about $0.0002 per session on Opus 5.5. 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 commands, from other repositories
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…
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.
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/…
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.
token-scan
Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Runs automated tokenscanner.py + manual 8-class audit. Usage: /token-scan [--chain solana].
validate
Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.