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 skills add zjp1997720/zhijian-skills --skill gpt56-sol-pro-consultgit clone --depth 1 https://github.com/zjp1997720/zhijian-skillsWrote 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/zjp1997720/zhijian-skills/gpt56-sol-pro-consult)<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/gpt56-sol-pro-consult"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/gpt56-sol-pro-consult/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/zjp1997720/zhijian-skills/gpt56-sol-pro-consult"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/gpt56-sol-pro-consult.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 | $0.00125 | $0.01718 |
| Opus 5 | $0.00063 | $0.00859 |
| Sonnet 5 | $0.00025 | $0.00344 |
| Haiku 4.5 | $0.00013 | $0.00172 |
Grade A, and why
gpt56-sol-pro-consult 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 12d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GPT 5.6 Sol Pro Consult
Ask GPT 5.6 Sol Pro to review a difficult problem with the evidence it needs, then bring the result back into the local Agent workflow. Treat the answer as advisory. The local Agent owns verification, adoption, and final delivery.
Routing contract
Use the Codex Chrome plugin by default for every consultation, including text-only requests. Read and follow the installed chrome:control-chrome Skill before browser work, then read Chrome workflow.
Use OpenCLI only when one of these is true:
- The user explicitly requests OpenCLI.
- The Codex Chrome plugin is unavailable or disconnected, and
opencli doctorconfirms a working browser bridge.
When OpenCLI is eligible, read OpenCLI fallback. Do not choose OpenCLI merely because it is installed. Do not use OpenCLI for file uploads.
If neither path is available, prepare the context packet and tell the user exactly which browser connection is missing. Never imply that a Pro consultation completed.
Requirements
- The default path requires Codex with the Chrome plugin connected.
- The selected Chrome profile must be logged into ChatGPT Web.
- The account must expose
Proin the standard ChatGPT model picker. - OpenCLI is optional and is not an installation prerequisite.
Hard gates
Model truthfulness
In standard ChatGPT conversations, OpenAI maps Pro to GPT 5.6 Sol Pro. Confirm either:
- a GPT 5.6-specific Pro test ID is checked; or
- the picker shows the
GPT-5.6 Solfamily and the exactProradio hasaria-checked=true.
Reject legacy GPT 5.5 Pro selectors, Pro Extended, base Sol Extra High, and ambiguous Pro text outside the model picker. Stop if the model cannot be confirmed.
Artifact truthfulness
ChatGPT Web cannot read a local path by itself. Upload the actual file, paste its contents, or build a text bundle. Never claim GPT inspected a file when it received only a filename, path, or summary.
What ships with it
11 files 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.
- agents/openai.yaml 278 B
- evals/evals.json 3.3 KB
- references/chrome-workflow.md 6.5 KB
- references/context-packet-template.md 1.4 KB
- references/opencli-fallback.md 1.7 KB
- scripts/build_attachment_bundle.py 5.3 KB runs code
- scripts/check_packet_safety.py 4.3 KB runs code
- scripts/extract_chatgpt_reply.py 3.0 KB runs code
- scripts/run_gpt56_sol_pro_consult.py 12 KB runs code
- tests/test_model_selection.py 1.8 KB runs code
- tests/test_skill_contract.py 2.6 KB runs code
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.
- 12d ago First seen · 145 lines · 125 tokens per session scan A b2d519edc8e1
gpt56-sol-pro-consult is a skill published in the GitHub repository zjp1997720/zhijian-skills (680 stars, last pushed 7d ago), licensed MIT. It adds 125 tokens to every session and 1,718 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…