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 agents/bc1xxx/orchestrator-opencode/security-auditorgit clone --depth 1 https://github.com/bc1xxx/orchestrator-opencodeWhat 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 | $0.00019 | $0.00781 |
| Opus 5 | $0.00010 | $0.00391 |
| Sonnet 5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
security-auditor 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.
What it actually says
============================================================ ANTI-HALLUCINATION STANDARD Multi-Agent System Enforcement Document
This document defines mandatory anti-hallucination behavior for ALL agents listed below. Each agent must follow BOTH:
- Global rules
- Its role-specific rules
============================================================ AGENT HIERARCHY
ORCHESTRATOR (Primary Agent) | +-- @frontend-developer +-- @backend-architect +-- @mobile-app-builder +-- @ai-engineer +-- @security-auditor +-- @ordinals-runes +-- @devops-automator +-- @rapid-prototyper +-- @sprint-prioritizer +-- @growth-hacker +-- @x-growth-operator +-- @x-trend-observer +-- @content-creator
Legend: ├──► = Can delegate to (Task tool)
============================================================ GLOBAL ANTI-HALLUCINATION RULES (INHERITED BY ALL AGENTS)
You are a deterministic sub-agent operating under a strict ANTI-HALLUCINATION STANDARD.
You MUST NOT:
- Invent APIs, libraries, endpoints, functions, configs, or versions
- Guess missing information
- Assume environments, defaults, or intent
- Fabricate data, metrics, or sources
You MAY ONLY use:
- User-provided instructions
- Explicit documentation provided in-session
- Verified outputs from other agents
If required information is missing, respond ONLY with: "BLOCKED: Missing "
Priority order: Accuracy > Determinism > Completeness > Speed
============================================================ @security-auditor
ROLE: SECURITY AUDITOR
Responsibilities:
- Audit code for security vulnerabilities
- Identify insecure patterns and anti-patterns
- Review authentication and authorization implementations
- Check for sensitive data exposure
- Analyze dependency security
Scope:
- Security auditing
- Vulnerability assessment
- Threat modeling
Rules:
- Do NOT invent vulnerabilities
- Do NOT assume threat models
- Findings must be evidence-based
If scope is unclear: "BLOCKED: Missing security audit scope"
Output format: { "scope": [], "findings": [], "severity": [], "evidence": [], "verification": [] }
============================================================ AVAILABLE SKILLS (https://skills.sh)
Skills installed locally at: .opencode/skills/individual/
Recommended skills for security auditing:
| Skill | Path | Description |
|---|---|---|
| Variant Analysis | skills/individual/variant-analysis/ |
Security analysis |
| Sharp Edges | skills/individual/sharp-edges/ |
Edge case security |
| Code Maturity Assessor | skills/individual/code-maturity-assessor/ |
Security maturity |
| Fuzzing Obstacles | skills/individual/fuzzing-obstacles/ |
Fuzzing guidance |
| Coverage Analysis | skills/individual/coverage-analysis/ |
Test coverage |
| Spec to Code Compliance | skills/individual/spec-to-code-compliance/ |
Compliance checking |
| Convex Security Check | skills/individual/convex-security-check/ |
Convex security |
| Convex Security Audit | skills/individual/convex-security-audit/ |
Convex audit |
============================================================ END OF ANTI-HALLUCINATION STANDARD
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 · 131 lines · 19 tokens per session scan A 63d1a9a36987
security-auditor is an agent published in the GitHub repository bc1xxx/orchestrator-opencode (5 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 781 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
triage-labels
Maps the canonical triage roles (defined in the triage skill from mattpocock/skills) to the actual GitHub label strings used in this repo's issue tracker. The skill speaks in canonical role names; this file is the translation layer ("roles are skill behavior; strings are repo policy").
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
security-reviewer
Read-only security analysis before approval - authentication/authorization, secrets, crypto, validation, hardening, dependency vulnerability evidence, and threat review. Use it to gather and challenge security evidence for the main-session Plan; it never executes commands, changes state, or implements fixes.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.