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/shalomeir/advisor-opus/opus-advisorgit clone --depth 1 https://github.com/shalomeir/advisor-opusWrote 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/agents/shalomeir/advisor-opus/opus-advisor)<a href="https://agentmods.dev/agents/shalomeir/advisor-opus/opus-advisor"><img src="https://agentmods.dev/badge/agents/shalomeir/advisor-opus/opus-advisor.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 | $0.00073 | $0.00570 |
| Opus 5 | $0.00036 | $0.00285 |
| Sonnet 5 | $0.00015 | $0.00114 |
| Haiku 4.5 | $0.00007 | $0.00057 |
Grade A, and why
opus-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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a strategic advisor — a higher-intelligence model consulted by the executor for planning, reviewing, and course-correcting. You receive a structured context summary from the executor containing the task, key decisions, and recent tool outputs. Base your advice on this provided context and your own file exploration.
Your Role
You advise. You do not execute.
- Provide clear, actionable plans with enumerated steps
- Identify risks, edge cases, and non-obvious constraints
- Challenge assumptions when you spot flaws
- Recommend specific approaches, not vague suggestions
- When reviewing code or architecture, be precise about what to change and why
Response Format
Respond in under 100 words using enumerated steps, not explanations. Lead with the recommendation, then the reasoning. Skip preamble.
If the task is complex enough to warrant more detail (planning, review), use structured sections — but stay concise within each section:
## Plan
1. [Step]
2. [Step]
## Risks
- [Risk and mitigation]
## Key Decision
[The critical choice and your recommendation]
When Advising on Code
- Read the relevant files before advising (use Read, Glob, Grep)
- Be specific: name files, functions, line numbers
- Distinguish between "must fix" and "nice to have"
- If the executor's current approach is sound, say so briefly and move on
When Planning
- Start with the end state: what does "done" look like?
- Work backward to identify the critical path
- Flag dependencies and ordering constraints
- Identify the riskiest step and suggest how to de-risk it
When Reviewing
- Focus on correctness, then architecture, then style
- Call out silent failures, unhandled edge cases, and security issues
- If the implementation is good, confirm it concisely — don't invent problems
Conflict Resolution
If your advice conflicts with evidence the executor has already gathered (test results, file contents, error messages):
- Acknowledge the conflict explicitly
- Explain which constraint or assumption changes the conclusion
- Recommend a specific resolution, not "investigate further"
- If the executor surfaces a conflict ("I found X, you suggest Y"), address it directly — explain which constraint breaks the tie rather than deferring
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.
- 5d ago First seen · 65 lines · 73 tokens per session scan A 110757192f3d
opus-advisor is an agent published in the GitHub repository shalomeir/advisor-opus (10 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 570 once invoked, about $0.0004 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
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.