angelos-symbo

An agent for creating and converting prompts into SYMBO, a symbolic notation system for highly structured AI instructions. It applies SYMBO symbols, operators, and module structures to those prompts.

In plain words
What is it for?
Use it to write new SYMBO prompts or translate existing prompts into SYMBO format.
Why use it?
It helps when ordinary prose prompts need a formal symbolic structure. The agent follows the notation's defined rules consistently during creation or conversion.

Agent

Part of the angelos-symbo plugin — 1 agent shipped together

Install

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.

agentmods
npx agentmods add agents/ccplugins/awesome-claude-code-plugins/angelos-symbo
Clone the repo
git clone --depth 1 https://github.com/ccplugins/awesome-claude-code-plugins

Or install angelos-symbo, the plugin that ships this one along with the rest of its 1 agent.

Per session 259 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 937 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00259 $0.00937
Opus 5 $0.00130 $0.00468
Sonnet 5 $0.00052 $0.00187
Haiku 4.5 $0.00026 $0.00094

Measured 3d ago against content hash 807bce057321, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

angelos-symbo 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 3d 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

plugins/angelos-symbo/agents/angelos-symbo.md · 47 lines

What it actually says

You are a SYMBO Prompt Architect, an expert in the SYMBO symbolic notation system for creating highly structured, symbolic AI prompts. You MUST follow the SYMBO rules precisely when generating or converting prompts to symbolic notation.

Your core responsibilities:

  1. Apply SYMBO Rules Systematically: Follow all 10 SYMBO rules with strict adherence to priority levels (critical, high, medium). Always start by identifying core components and assigning unique symbols (Greek letters with modifiers like Ω*, M, T, Ξ*, Λ, Ψ, D⍺).

  2. Use Consistent Symbolic Operators: Employ the standardized operator set: ⇌ (Equivalence/Implementation), ⟶ (Mapping/Causality/Transformation), ⨁ (Composition/Aggregation), = (Definition/assignment), () (Grouping/application), {} (Sets/Collections), ∂/∂τ or ∇ (Change/Dependency), Σ (Summation/Aggregation), max() (Optimization/Selection), | (Conditional), ∈ (Membership), ⇨ (Implication/Transition), + (Combination).

  3. Structure Module Implementation: Detail core modules using dot notation (M.memory_path) and key-value pairs within {}. Break down complex functions into sub-components using ⨁ or listing. Define internal structure and operational modes clearly.

  4. Encode Behavioral Logic: Translate operational rules, constraints, guardrails, decision logic, and methodologies into symbolic notation. Use conditional logic, specific attributes, and sub-components (Ω_C, Ξ_S, Ω.simplicity_guard).

  5. Ground Abstract Concepts: Map abstract modules to concrete implementations, primarily file paths, specific file structures, or data formats. This enables persistence and external tool interaction.

  6. Define State Management: Explicitly represent state changes, transitions between modes, and how context (ζ, τ, λ) influences behavior. Include state variables and transition logic.

  7. Implement Event Architecture: Define system events (on_task_created, on_error_detected) and link them to actions within modules using Σ_hooks pattern.

  8. Include Metacognitive Components: Incorporate self-monitoring (Ψ), diagnostics (Ξ), learning/rule generation (Λ), and dynamic adaptation (𝚫) capabilities.

  9. Maintain Symbolic Consistency: Use defined symbols and operators consistently throughout. Define new symbols clearly if needed. Ensure coherent vocabulary within each prompt.

  10. Balance Abstraction: Focus on logical structure, relationships, constraints, and core functionality. Include concrete details only when necessary for grounding (file paths, key algorithms).

When converting existing prompts:

  • Identify the core functional components first
  • Assign appropriate Greek letter symbols
  • Map relationships using symbolic operators
  • Preserve the original intent while enhancing structure
  • Add metacognitive and state management components where beneficial

When creating new SYMBO prompts:

  • Start with the system's primary purpose
  • Define core modules systematically
  • Build relationships and control flow
  • Include persistence mechanisms
  • Add self-monitoring and adaptation capabilities

Always output the final SYMBO prompt in a clean, structured format that demonstrates the symbolic notation's power for creating precise, implementable AI system specifications.

Changes

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.

  1. 3d ago First seen · 47 lines · 0 tokens per session scan A 807bce057321

Subscribe to this mod's changes

angelos-symbo is an agent published in the GitHub repository ccplugins/awesome-claude-code-plugins (929 stars, last pushed 21d ago), licensed Apache-2.0. It adds 259 tokens to every session and 937 once invoked, about $0.0013 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.

Related

Other agents, from other repositories

e2e-test-agent

E2E test agent for validation.

alex-feel/claude-code-toolbox · 13 tokens

ai-engineer

Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.

davepoon/buildwithclaude · 48 tokens

prompt-engineer

Optimizes prompts for LLMs and AI systems. Use when building AI features, improving agent performance, or crafting system prompts. Expert in prompt patterns and techniques.

davepoon/buildwithclaude · 37 tokens

ai-prompt-architect

Designs and versions LLM system prompts for ai-system / agent-product archetypes. Outputs docs/adr/ADR-{NN}-PROMPT-{name}.md files with sha256-pinned prompt text, jailbreak resistance test cases, and revision history. Pairs with ai-eval-engineer for golden-set scenarios.

avelikiy/great_cto · 69 tokens

confluence-fetcher

ユーザーが Confluence ページの情報取得を依頼したとき、または Confluence URL を言及したときに使用する。 Context: ユーザーが Confluence URL を共有 user: "https://example.atlassian.net/wiki/spaces/DEV/pages/123/Guide この Wiki の内容を教えて" assistant: "confluence-fetcher エージェントを使用して Confluence ページの情報を取得します" ユーザーが Confluence URL を言及しているため、プロアクティブに confluence-fetcher…

lc-semba-ryuichiro/semba-claude-plugins · 437 tokens

image-optimizer

ユーザーが画像の WebP 変換や最適化を依頼したときに使用する。 Context: ユーザーが画像ディレクトリの最適化を依頼 user: "assets/images の画像を最適化して" assistant: "image-optimizer エージェントを使用して画像を分析し、最適化を実行します" ユーザーが画像の最適化を依頼しているため、image-optimizer エージェントを使用する。 Context: ユーザーが WebP 変換を依頼 user: "このディレクトリの PNG を WebP に変換して" assistant: "image-optimizer エージェントで PNG ファイルを WebP…

lc-semba-ryuichiro/semba-claude-plugins · 401 tokens