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.
git 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/commands/shalomeir/advisor-opus/advise)<a href="https://agentmods.dev/commands/shalomeir/advisor-opus/advise"><img src="https://agentmods.dev/badge/commands/shalomeir/advisor-opus/advise.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 | $0.00067 | $0.00724 |
| Opus 5 | $0.00034 | $0.00362 |
| Sonnet 5 | $0.00013 | $0.00145 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
advise 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 8d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route this request to the advisor-opus:opus-advisor subagent.
IMPORTANT: The advisor agent starts fresh with NO conversation history. You (the executor) must build the context.
Raw user request: $ARGUMENTS
Context Gathering (executor does this BEFORE spawning the advisor)
The advisor starts with zero context — it cannot see your conversation at all. You must pass it everything it needs. Follow these three steps in order:
Step 1 — Task summary (1-2 sentences): Write what the user is trying to do. Example: "User is adding OAuth2 login to a Next.js app."
Step 2 — Key facts (bullet list, keep short): List what you know so far — files found, approaches tried, what worked/failed. Compress old history into short bullets.
Step 3 — Recent raw output (copy-paste, do NOT summarize): Copy the last 3-5 tool results exactly as they appeared — file contents, grep results, error messages. The advisor needs the actual text, not your summary of it. If a tool returned 50 lines, include all 50 lines.
Optional: run git diff --stat and git status to show current state.
Structure the advisor prompt as:
## Task
[1-2 sentence summary of the session goal]
## Background
- [compressed key decisions and findings]
- [what was tried, what failed]
- [current approach and status]
## Recent Context (verbatim)
[last 3-5 tool calls/results, errors, user messages — raw, uncompressed]
## Question
[user's $ARGUMENTS, or "What should I do next?"]
Routing Rules
- Build the context as described above.
- If
$ARGUMENTSis provided, include it as the## Questionsection. - If
$ARGUMENTSis empty, set the question to: "Review the current situation. Provide strategic guidance on the best approach, flag any risks, and suggest next steps." - Spawn the
advisor-opus:opus-advisorsubagent with the full structured prompt. - Return the advisor's response verbatim. Do not summarize, filter, or add commentary.
- After returning the advice, do not take any further action — let the user decide how to proceed.
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.
- 8d ago First seen · 62 lines · 67 tokens per session scan A 553947de78df
advise is a command published in the GitHub repository shalomeir/advisor-opus (10 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 724 once invoked, about $0.0003 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.