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 rojim666/SztuCode --skill recommend-expertsgit clone --depth 1 https://github.com/rojim666/SztuCodeWrote 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/rojim666/sztucode/recommend-experts)<a href="https://agentmods.dev/skills/rojim666/sztucode/recommend-experts"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/recommend-experts/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/rojim666/sztucode/recommend-experts"><img src="https://agentmods.dev/badge/skills/rojim666/sztucode/recommend-experts.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00047 | $0.00655 |
| Opus 5.5 | $0.00019 | $0.00262 |
| Sonnet 5.5 | $0.00009 | $0.00131 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
recommend-experts 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 1mo 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recommend Experts
Use this Skill only when a specialist role or multi-role workflow would clearly improve the current task and no Expert is selected in the current session.
Workflow
- Confirm that no Expert is selected in the current session. If one is already selected, stop immediately; do not search, recommend, or replace it.
- Call
search_pluginswithtypeset toexpert. Put the user's request inuserIntent; addkeywordsonly when useful. - Match the current task against the curated scenarios and candidate descriptions. Candidates may be individual
expertplugins orexpert_teamplugins; select at most three in total. - Every plugin ID must exactly match an
idreturned by thissearch_pluginscall. - Call
suggest_plugin_installexactly once to render one Expert card. If recommending multiple candidates, include all of them in this single call:
{
"type": "expert",
"contextLabel": "For this deep-research task",
"pluginId1": "DeepResearchExpert",
"pluginId2": "GPTResearcherTeam"
}
suggest_plugin_install Schema
Follow this schema exactly:
{
"type": "object",
"additionalProperties": false,
"properties": {
"type": {
"type": "string",
"enum": ["connector", "expert"]
},
"contextLabel": {
"type": "string"
},
"pluginId1": { "type": "string" },
"pluginId2": { "type": "string" },
"pluginId3": { "type": "string" }
},
"required": ["type", "pluginId1"]
}
One call can recommend at most three candidates. Never pass arrays, plugins, pluginIds, or an { "item": ... } wrapper.
Rules
- Never invoke
suggest_plugin_installmore than once in the same response, whether sequentially or in parallel. - A single
suggest_plugin_installcall can recommend one to three candidates by usingpluginId1,pluginId2, andpluginId3. - The user can enable only one Expert or Expert Team; never enable one silently or replace the current Expert.
- Do not replace the
suggest_plugin_installcard with a text list. - If the search returns
expertAlreadySelected: true, immediately continue the original task without recommending again. - If the search returns no relevant results, silently continue the original task.
- After the user skips, times out, or cancels, do not recommend the same candidates again in the same response.
- Never use web search to find Plugins;
search_pluginsis the only source for candidates.
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.
- 1mo ago First seen · 67 lines · 47 tokens per session scan A 0481a4d3f335
recommend-experts is a skill published in the GitHub repository rojim666/SztuCode (110 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 655 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-12.
Other skills, from other repositories
codex-delegate
Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Codex — phrasings like "have Codex do X", "delegate this to Codex", "run it through Codex", or "use Codex to implement/fix/refactor" …
commandcode-delegate
Delegate a coding task to the Command Code CLI (cmd) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Command Code — phrasings like "have Command Code do X", "delegate this to commandcode", "run it through cmd", or "use Command Code…
claude-delegate
Delegate a coding task to a separate Claude Code CLI process or another Claude session as an implementer, then review its diff and land it yourself. Use only when the user explicitly asks to delegate implementation to Claude Code, another Claude session, or the claude CLI — for example, "have another Claude implement…
copilot-delegate
Delegate a coding task to the GitHub Copilot CLI (copilot) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Copilot - phrasings like "have Copilot implement X", "delegate this to copilot", "run it through Copilot CLI", or "use…
cursor-delegate
Delegate a coding task to the Cursor Agent CLI (cursor-agent) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Cursor — phrasings like "have Cursor implement X", "delegate this to Cursor", "run it through Cursor Agent", or "use…
cline-delegate
Delegate a coding task to the Cline coding agent CLI (cline) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to delegate implementation work to Cline - phrasings like "have Cline implement X", "delegate this to cline", "run it through Cline", or "use cline to…