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 athola/claude-night-market --skill gemini-delegationgit clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/athola/claude-night-market/gemini-delegation)<a href="https://agentmods.dev/skills/athola/claude-night-market/gemini-delegation"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/gemini-delegation/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/athola/claude-night-market/gemini-delegation"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/gemini-delegation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Excessive Agency · line 92 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Agent Snooping · line 27 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 28 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 29 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 30 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00035 | $0.00906 |
| Opus 5 | $0.00017 | $0.00453 |
| Sonnet 5 | $0.00007 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
gemini-delegation 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Table of Contents
Gemini CLI Delegation
Overview
This skill implements conjure:delegation-core for the Gemini CLI.
It provides Gemini-specific authentication, quota management,
and command construction.
For shared delegation patterns, see Skill(conjure:delegation-core).
When To Use
- After
Skill(conjure:delegation-core)determines Gemini is suitable - When you need Gemini's large context window (1M+ tokens)
- For batch processing, summarization, or pattern extraction tasks
- If the
geminiCLI is installed and authenticated
When NOT To Use
- Choosing which provider to delegate to (use
conjure:delegation-core) - Qwen was the selected provider (use
conjure:qwen-delegation)
Prerequisites
Installation:
# Verify installation
gemini --version
# Check authentication
gemini auth status
# Login if needed
gemini auth login
# Or set API key
export GEMINI_API_KEY="your-key"
Verification: Run the command with --help flag to verify availability.
Quick Start
Basic Command
# File analysis
gemini -p "@path/to/file Analyze this code"
# Multiple files
gemini -p "@src/**/*.py Summarize these files"
# With specific model
gemini --model gemini-3-pro -p "..."
# JSON output
gemini --output-format json -p "..."
Save Output
gemini -p "..." > delegations/gemini/$(date +%Y%m%d_%H%M%S).md
Gemini-Specific Details
For Gemini-specific models, CLI options, cost reference,
and troubleshooting, see modules/gemini-specifics.md.
Exit Criteria
-
gemini --versionexits 0 before any task is delegated, and a missing installation is reported and stops execution. - Authentication is judged from
GEMINI_API_KEYand from the delegation's own exit code, never fromgemini auth status. That command exits 0 while printingError authenticating: ProjectIdRequiredErrorover a credential that cannot be used, so its status is not evidence.delegation-core's shared module states the rule: authentication is never decided by running a provider's own CLI. - The delegated task output is saved to
delegations/gemini/YYYYMMDD_HHMMSS.md(timestamp format matching the Quick Start example), and that file exists on disk after the delegation completes. - If
conjure:delegation-coreselected a different provider (Qwen or local), this skill is not invoked; Gemini delegation only runs when delegation-core explicitly routes to Gemini. - Tasks requiring > 1M tokens in context are flagged before submission; the skill reports the estimated token count and confirms it falls within Gemini's supported window.
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 · 125 lines · 35 tokens per session scan A 78b97de912fd
gemini-delegation is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 906 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
conductor-new-track
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.
swarm-improve
End-to-end project improvement — plan, branch, delegate execution, verify. Calls /plan for analysis, then delegates fixes to agents. Use when "improve project", "swarm improve", "send agents to fix", "refactor project X", "upgrade project". Do NOT use for planning only (use /plan), single tasks (use /delegate), or own…
solo-skill-audit
Audit a skill against Anthropic's best practices checklist — 12 dimensions, scored 0-24. Use when user says "audit skill", "review skill quality", "check skill", "skill score", "skill checklist", or "is this skill good". Do NOT use for KB audits (use /audit) or code review (use /review).
ccb-compact
Compact CCB managed agent conversation context with ccb compact. Use when the user writes $ccb-compact, $ccbcompact, or asks to summarize one or more mounted agent contexts without restarting agents or deleting project state.
node-check
Verify one CCB worker node and reject hidden fallback, degradation, scope shrinkage, or missing evidence.
bounded-work-item
Execute one bounded CCB work item and report evidence without changing workflow authority.