Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/instructions/vzwjustin/advisor/claude-md)<a href="https://agentmods.dev/instructions/vzwjustin/advisor/claude-md"><img src="https://agentmods.dev/badge/instructions/vzwjustin/advisor/claude-md.svg" alt="Measured on agentmods" 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 | $0.02361 | $0.02361 |
| Opus 5 | $0.01180 | $0.01180 |
| Sonnet 5 | $0.00472 | $0.00472 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade A, and why
advisor CLAUDE.md 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Advisor — Opus-led Agent Team (Claude Code Native)
Environment & Commands
Running tests
uv run pytest fails with "Failed to spawn: pytest" unless dev extras are installed.
Always use: uv sync --extra dev && uv run pytest -x -q
After editing advisor/orchestrate/_prompts/advisor.txt or any prompt builder, regenerate snapshots:
ADVISOR_UPDATE_SNAPSHOTS=1 uv run pytest tests/test_prompt_snapshots.py
Local install (two-step)
uv tool install --reinstall --from /Users/justinadams/Downloads/advisor advisor-agent
advisor install # refreshes SKILL.md + CLAUDE.md nudge
Registry install (post-PyPI publish): UV_NO_CACHE=1 uv tool install --force advisor-agent
Git workflow
Uncommitted changes block rebase/merge every time — always stash first:
git stash && git pull --rebase origin main && git stash pop
Advisor pipeline gotchas
SendMessagewith a stringmessagerequires asummaryparam or it errors:summary is required when message is a string- Agent
modelfield: only bare aliases (opus,sonnet,haiku) or full IDs (claude-opus-4-8) — mid-form strings likeopus-4-8error (advisor CLI normalizes these automatically) CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1must be set in env for TeamCreate/TeamDelete/SendMessage
Large files (>800 LOC → 3-fix cap in advisor pipeline)
advisor/__main__.py~3400–3600 LOCadvisor/rank.py~1186 LOCadvisor/install.py~890 LOCadvisor/orchestrate/runner_prompts.py~813 LOC
Rust port
cargo test accepts only one test-name pattern; cargo test foo bar errors — use single name or no filter.
Two-model team using Claude Code's TeamCreate/Agent/SendMessage. No external API calls.
Models configurable via TeamConfig(advisor_model=, runner_model=) — defaults: claude-opus-4-8 / claude-sonnet-4-6. Claude Code's Agent() tool accepts bare aliases (opus, sonnet, haiku) for "always-latest" or full claude-<family>-<version> IDs to pin a specific version; mid-form strings like opus-4-5 are not accepted.
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.
- 6d ago First seen · 234 lines · 2,361 tokens per session scan A fd9228698dad
advisor CLAUDE.md is an instructions file published in the GitHub repository vzwjustin/advisor (10 stars, last pushed 1mo ago), licensed MIT. It adds 2,361 tokens to every session, about $0.0118 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 instructions, from other repositories
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
autopus-adk GEMINI.md
Gemini CLI instructions for Insajin/autopus-adk, covering autopus-adk harness, 스킬 디렉터리, core guidelines, subagent delegation and file size limit.
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
nanobot CLAUDE.md
Claude Code instructions for HKUDS/nanobot, a project described as: Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps.
rustyhand AGENTS.md
AGENTS.md instructions for ginkida/rustyhand, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.