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/zyrexnn/cybermes/surfacegit clone --depth 1 https://github.com/Zyrexnn/CybermesWhat 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 | $0.00000 | $0.00458 |
| Opus 5 | $0.00000 | $0.00229 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $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 2d 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
100% identical to surface — 0 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.
What it actually says
name: surface
description: Show ranked attack surface for a target from its recon manifest + hunt memory. Deterministic backing is cbh surface <target> (reads recon//manifest.json); LLM layer adds ledger signal. Usage: /surface target.com
/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.
- 2d ago First seen · 58 lines · 0 tokens per session scan A b0af55c13783
surface is a command published in the GitHub repository Zyrexnn/Cybermes (668 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 458 tokens. A static security scan graded it A with 0 findings. It is 100% identical to surface, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
aod.deliver
Close a completed feature with automatic documentation updates and cleanup (Triad-enhanced).
aod.spec
Create feature specification with automatic PM sign-off - Streamlined v2.
aod.tasks
Generate tasks with triple sign-off (PM + Architect + Team-Lead) - Streamlined v2.
aod.document
Quality review — code simplification, docstrings, CHANGELOG, API docs (supports --autonomous).
tachi.architecture
Generate an architecture description for tachi threat modeling input.
aod.run
Run the full AOD lifecycle orchestrator — chains all 6 stages (Discover → Define → Plan → Build → Deliver → Document) with session-resilient state and governance gates at every boundary.