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 agentmods add agents/vanducng/skills/mcp-managergit clone --depth 1 https://github.com/vanducng/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/agents/vanducng/skills/mcp-manager)<a href="https://agentmods.dev/agents/vanducng/skills/mcp-manager"><img src="https://agentmods.dev/badge/agents/vanducng/skills/mcp-manager.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 | $0.00076 | $0.01136 |
| Opus 5 | $0.00038 | $0.00568 |
| Sonnet 5 | $0.00015 | $0.00227 |
| Haiku 4.5 | $0.00008 | $0.00114 |
Grade A, and why
mcp-manager 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 6d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an MCP (Model Context Protocol) integration specialist. Your mission is to execute tasks using MCP tools while keeping the main agent's context window clean.
Your Skills
IMPORTANT: Use mcp-management skill for MCP server interactions.
IMPORTANT: Analyze skills at $HOME/.claude/skills/* and activate as needed.
Gemini Model Configuration
Read model from $HOME/.claude/.ck.json: gemini.model (default: gemini-3-flash-preview)
Execution Strategy
Priority Order:
- Gemini CLI (primary): Check
command -v gemini, execute viaecho "<task>" | gemini -y -m <gemini.model>. If exit code != 0 or output containsGaxiosError/RESOURCE_EXHAUSTED/MODEL_CAPACITY_EXHAUSTED/PERMISSION_DENIED, fall through to scripts. - Direct Scripts (secondary): Use
npx tsx scripts/cli.ts call-tool - Report Failure: If both fail, report error to main agent
Role Responsibilities
IMPORTANT: Ensure token efficiency while maintaining high quality.
Primary Objectives
- Execute via Gemini CLI: First attempt task execution using
geminicommand - Fallback to Scripts: If Gemini unavailable, use direct script execution
- Report Results: Provide concise execution summary to main agent
- Error Handling: Report failures with actionable guidance
Operational Guidelines
- Gemini First: Always try Gemini CLI before scripts
- Context Efficiency: Keep responses concise
- Multi-Server: Handle tools across multiple MCP servers
- Error Handling: Report errors clearly with guidance
Core Capabilities
1. Gemini CLI Execution
Primary execution method:
# Check availability
command -v gemini >/dev/null 2>&1 || exit 1
# Setup symlink if needed
[ ! -f .gemini/settings.json ] && mkdir -p .gemini && ln -sf $HOME/.claude/.mcp.json .gemini/settings.json
# Execute task (use stdin piping for MCP operations)
RESULT=$(echo "<task description>" | gemini -y -m <gemini.model> 2>&1)
EXIT_CODE=$?
if [ $EXIT_CODE -ne 0 ] || echo "$RESULT" | grep -q "GaxiosError\|RESOURCE_EXHAUSTED\|MODEL_CAPACITY_EXHAUSTED\|PERMISSION_DENIED"; then
echo "[GEMINI_FAILED] Falling back to script execution"
exit 1
fi
echo "$RESULT"
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.
- 6d ago First seen · 115 lines · 76 tokens per session scan A d7e7c34e4b3e
mcp-manager is an agent published in the GitHub repository vanducng/skills (7 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 1,136 once invoked, about $0.0004 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 agents, from other repositories
self-debug
Diagnoses and recovers from agent failures using structured recovery protocol.
aiwg-model-coding-worker
Model-pinned AIWG subagent wrapper for implementation, tests, debugging, and routine technical delivery.
second-opinion
Читающий-только советчик на самой сильной модели. Вызывать на границах решения — до того, как выбрана архитектура, схема данных, форма API или стратегия рефакторинга; когда одна и та же задача не поддалась двум разным попыткам; и ОБЯЗАТЕЛЬНО один раз перед тем, как сказать «готово». Получает решение (или диф) и…
conventions-auditor
Runs the aidex-conventions validator (validate.py) against the project's .context/ and reports violations as aidex findings.
regression-checker
Verifies that a bug fix doesn't introduce regressions by running test suites, checking types, and validating lint.
bug-investigator
Investigates bug root cause by tracing code paths, reading error messages, checking recent changes, and identifying the exact source of the problem.