Borrowing it
Nothing to install: this file belongs to KonghaYao/peri. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/KonghaYao/peri/main/.claude/skills/advisor-consultation/SKILL.mdgit clone --depth 1 https://github.com/KonghaYao/periWrote 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/skills/konghayao/peri/advisor-consultation)<a href="https://agentmods.dev/skills/konghayao/peri/advisor-consultation"><img src="https://agentmods.dev/badge/skills/konghayao/peri/advisor-consultation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/konghayao/peri/advisor-consultation"><img src="https://agentmods.dev/badge/skills/konghayao/peri/advisor-consultation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00057 | $0.01016 |
| Opus 5 | $0.00028 | $0.00508 |
| Sonnet 5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
advisor-consultation 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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consulting the Advisor
Use a tool-free Opus advisor to improve a decision, not to outsource exploration or execution. The main agent remains responsible for repository inspection, scope, security, implementation, verification, and the final decision.
Trigger decision
| Situation | Action |
|---|---|
| User explicitly requests an advisor, second opinion, or Opus review | Consult once. |
| Cross-crate/API contract, event/prompt/tool boundary, security-sensitive, concurrency/lifecycle decision, or two credible options with material trade-offs | Consult after exploration. |
| Two reasonable investigations failed to distinguish the root cause | Consult after recording their outcomes. |
| Local, reversible change with a clear tested path | Do not auto-consult. |
| Advisor would need to inspect the repository to answer | Gather the missing evidence first; do not ask it to guess. |
For an extreme-risk decision, the main agent may collect the advisor's requested minimum evidence and consult again. Do not loop merely to seek agreement.
Prepare the decision packet
Before dispatching .claude/agents/advisor.md, inspect the relevant code, tests, contracts, and current diff. Send only the smallest packet that lets a tool-free advisor reason correctly:
# Advisor Decision Packet
## Task contract
- Goal:
- Success criteria:
- In scope / out of scope:
- Constraints, deadline, and risk:
## Evidence
- Code facts: `path:symbol` plus necessary excerpts.
- Tests, errors, command results, and current behavior:
- Affected interfaces, consumers, or compatibility requirements:
## Reasoning so far
- Candidate options:
- Attempts and their outcomes:
- Open questions and assumptions:
## Decision requested
- Exact choice or trade-off the advisor must evaluate:
Facts must include a source path, test name, command output, or another traceable origin. Label interpretations as assumptions. Before dispatch, scan the packet for secrets and sensitive material: credential-like assignments (KEY, TOKEN, SECRET, PASSWORD), authorization headers, cookies, PEM blocks, connection strings, complete environment dumps, raw traces, and unbounded stderr. If found, do not dispatch the packet; replace it with the smallest redacted or structural evidence needed for the decision. Never include secrets, tokens, passwords, connection strings, unredacted environment values, or unnecessary personal data.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 82 lines · 57 tokens per session scan A 6af1fccb12c8
advisor-consultation is a skill published in the GitHub repository KonghaYao/peri (163 stars, last pushed today), licensed Apache-2.0. It adds 57 tokens to every session and 1,016 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 2026-08-30.
Other skills, from other repositories
qa-testing
Verify your work by actually operating the app or website you changed, instead of assuming it works. Strongly recommended whenever you build, modify, or debug a web app, website, or desktop GUI app. Drive real browsers with the agent-browser CLI and native desktop apps with the cua-driver CLI. These are installed on…
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
skill-creator
Create or update a Codex skill with appropriately scoped instructions and any needed supporting resources.
codex-pr-body
Update the title and body of one or more pull requests.