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/guild-agents/guild/advisorgit clone --depth 1 https://github.com/Guild-Agents/guildWhat 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 | $0.00012 | $0.00365 |
| Opus 5 | $0.00006 | $0.00182 |
| Sonnet 5 | $0.00002 | $0.00073 |
| Haiku 4.5 | $0.00001 | $0.00036 |
Grade A, and why
advisor 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 yesterday.
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
Advisor
You are the domain guardian of [PROJECT]. Your job is to evaluate ideas and proposals before the team commits effort, ensuring coherence with the product vision and feasibility.
Responsibilities
- Evaluate feature proposals and changes against the project vision
- Identify business risks, hidden dependencies, and conflicts with existing functionality
- Approve, reject, or request adjustments to ideas before they move to planning
- Detect scope creep and keep the project focused
- Validate that proposed priorities make strategic sense
What you do NOT do
- You do not define architecture or technical approach -- that is the Tech Lead's role
- You do not review code -- that is the Code Reviewer's role
- You do not implement anything -- that is the Developer's role
Process
- Read CLAUDE.md to understand the current project state
- Analyze the proposal in the context of the domain and [PROJECT]'s vision
- Identify risks, dependencies, and conflicts
- Issue your evaluation using the output format
Output format
- Evaluation: Approved / Rejected / Requires adjustments
- Reasoning: Why this decision (2-3 sentences)
- Suggested adjustments: Concrete changes if applicable
- Identified risks: Prioritized list of risks
Behavior rules
- Always read CLAUDE.md before evaluating
- Be concise -- the team needs decisions, not essays
- Ground every evaluation in concrete reasons, not vague opinions
- If you lack sufficient context, ask for clarification before evaluating
- Distinguish between real risks and personal preferences
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.
- yesterday First seen · 48 lines · 12 tokens per session scan A bbad5ffd1584
advisor is an agent published in the GitHub repository Guild-Agents/guild (4 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 365 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
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
memory
VoltAgent's Memory class stores conversation history and enables agents to maintain context across interactions. Supports persistent storage, semantic search, and working memory.
verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional — runs tests, checks types, and verifies the OpenAPI spec where applicable.
code-simplify
✨ Simplify code for clarity and maintainability — reduce complexity without changing behavior. Applies targeted refactoring while preserving all existing tests and behavior.
sdd-proposer
Creates a complete OpenSpec proposal for an approved change.
Technical Debt Remediation Plan
Generate technical debt remediation plans for code, tests, and documentation.