Skill

third-party-call

Calls external AI tools (Claude CLI, Codex, Gemini) in non-interactive mode for independent code review, idea proposal, design analysis, and other tasks needing fresh context.

developer-tools

npx claudepluginhub sihaoliu/gaac --plugin gaac

Popularity

Stars

Forks

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/gaac:third-party-call

User invocable

Model invocable

Inline context

Default effort

Tool Access

This skill is limited to the following tools:

BashReadWrite

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

This skill provides a unified interface for invoking external AI tools in GAAC workflows. It manages:

Supporting Files

prompts/ANALYZER_PROMPT.mdprompts/CHECKER_PROMPT.mdprompts/CODE_REVIEWER_PROMPT.mdprompts/CODE_REVIEW_PROMPT.mdprompts/PEER_CHECK_PROMPT.mdprompts/PROPOSER_PROMPT.mdscripts/check-tools.shscripts/run-analysis.shscripts/run-code-review.shscripts/run-peer-check.shscripts/run-web-research.sh

SKILL.md

260 lines · ~1.9k tokens

Similar Skills

external-tools

270

Delegates implementation and review tasks to external AI CLI tools (Codex, Gemini) with cross-model adversarial review for cost savings and improved accuracy.

4 files

metaswarm

external-agents

101

Invokes OpenAI Codex and Google Gemini CLIs via Bash for second opinions, code reviews, and alternative analysis. Useful when users request external AI verification or explicitly say 'ask codex' or 'ask gemini'.

sc-skills

multi-ai-consultant

149

Consults Gemini 2.5 Pro, OpenAI Codex, and Claude for second opinions on debugging failures, architectural decisions, security validation, and fresh perspectives.

10 files4 tools

multi-ai-consultant

Stats

LanguageShell

Stars26

Forks3

MaintenancePoor

Last CommitJan 14, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Stats

Actions

Help us improve

Share bugs, ideas, or general feedback.

Third-Party Call Skill

This skill provides a unified interface for invoking external AI tools in GAAC workflows. It manages:

Tool Detection: Check which tools are available
Invocation Wrapper: Consistent interface for all tools
Security Controls: Read-only access, sandboxing
Output Capture: Structured output handling

Purpose

External tools provide:

Fresh Context: No conversation history bias
Independent Perspective: Different model, different thinking
Specialized Capabilities: Web search (Gemini), deep reasoning (Codex)

Supported Tools

Tool	Primary Use	Detection
`codex`	Code review, analysis	`which codex`
`claude`	Fallback for codex	`which claude`
`gemini`	Web research, proposals	`which gemini`

Scripts

Check Available Tools

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/check-tools.sh"

Run Analysis (Codex/Claude)

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/run-analysis.sh" \
    --prompt-file ./prompt.md \
    --output-file ./output.md \
    --tool codex \
    --context-files "src/**/*.ts"

Run Web Research (Gemini)

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/run-web-research.sh" \
    --topic "React state management best practices 2024" \
    --output-file ./research.md

Run Peer Check

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/run-peer-check.sh" \
    --issue-number 42 \
    --output-file ./peer-review.md

Run Code Review (Independent Scoring)

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/run-code-review.sh" \
    --issue-number 42 \
    --output-file ./code-review.md

Outputs structured markers:  and 

Role-Based Model Configuration

Model configuration is read from gaac.md. The --role parameter determines which model config to use:

Role	gaac.md Key	Default	Purpose
`analyzer`	`gaac.models.analyzer`	`codex:gpt-5.2-codex:high`	Synthesis and analysis
`analyzer` (fallback)	`gaac.models.analyzer_fallback`	`claude:opus`	Fallback for analyzer
`checker`	`gaac.models.checker`	`claude:opus`	Critical checking
`proposer`	`gaac.models.proposer`	`claude:sonnet`	Creative proposals
`proposer_secondary`	`gaac.models.proposer_secondary`	`gemini:gemini-3-pro-preview`	Secondary proposer (Gemini)
`code_reviewer`	`gaac.models.code_reviewer`	`codex:gpt-5.2-codex:high`	Independent code review
`code_reviewer` (fallback)	`gaac.models.code_reviewer_fallback`	`claude:opus`	Fallback for code review

Usage:

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/run-analysis.sh" \
    --role analyzer \
    --prompt-file ./prompt.md \
    --output-file ./output.md

Model Config Format: tool:model:reasoning (e.g., codex:gpt-5.2-codex:high)

Prompts

Prompt	Purpose
`prompts/CODE_REVIEWER_PROMPT.md`	100-point scoring rubric for code review
`prompts/CHECKER_PROMPT.md`	Critical checker for proposer-checker-analyzer debates

Tool Configurations

Codex (Preferred for Analysis)

codex exec \
    -m gpt-5.2-codex \
    -c model_reasoning_effort=high \
    --enable web_search_request \
    -s read-only \
    -o "$OUTPUT_FILE" \
    -C "$PROJECT_ROOT" \
    < prompt.txt

Features:

Deep reasoning (high effort)
Read-only sandbox
Web search capability
Output to file

Claude (Fallback)

claude -p \
    --model opus \
    --permission-mode bypassPermissions \
    --tools "Read,Grep,Glob,WebSearch,WebFetch" \
    --allowedTools "Read,Grep,Glob,WebSearch,WebFetch" \
    < prompt.txt > output.md

Features:

Read-only tools only
Web search capability
Output to stdout

Gemini (Web Research)

GEMINI_CLI_SYSTEM_SETTINGS_PATH="$TEMP_SETTINGS" \
gemini \
    --output-format json \
    --approval-mode yolo \
    "prompt" > output.json

Settings file:

{
  "tools": {
    "core": ["list_directory", "read_file", "glob", "search_file_content", "web_fetch", "google_web_search"],
    "exclude": ["write_file", "replace", "run_shell_command"]
  }
}

Features:

Google-powered web search
Read-only codebase access
No file modifications

Security Model

All external tools run with:

Capability	Allowed	Enforced By
Read codebase	Yes	Tool config
Search codebase	Yes	Tool config
Web search	Yes	Tool config
Write files	No	Sandbox/tool exclusion
Execute commands	No	Sandbox/tool exclusion

Use Cases

1. Peer Code Review (Phase 6.2)

Uses Codex (or Claude fallback) to review implementation:

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/run-peer-check.sh" --issue-number 42

Output: PASS/NEEDS_WORK with detailed findings

2. Design Proposal (Research Phase)

Uses Gemini for web-enhanced proposals:

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/run-web-research.sh" \
    --topic "distributed cache invalidation patterns" \
    --output-file ./proposal.md

3. Independent Analysis (Refinement Phase)

Uses Codex/Claude for synthesizing multiple inputs:

bash "${CLAUDE_PLUGIN_ROOT}/skills/third-party-call/scripts/run-analysis.sh" \
    --prompt-file ./analysis-prompt.md \
    --context-files "./docs/draft/*.md" \
    --output-file ./synthesis.md

Error Handling

Exit Code	Meaning	Action
0	Success	Use output
1	Tool not available	Try fallback
2	Tool execution failed	Try fallback
3	Invalid input	Fix and retry
4	Timeout	Increase timeout or simplify

Timeout Configuration

Tool	Default	Env Variable
Codex	5400s	`CODEX_TIMEOUT`
Claude	300s	`CLAUDE_TIMEOUT`
Gemini	300s	`GEMINI_TIMEOUT`

Integration Points

GAAC Stage	Third-Party Usage
Research	Gemini for web proposals
Refinement	Codex/Claude for analysis
Planning	Codex for design review
Work	Peer-check for code review

Files in This Skill

File	Purpose
`SKILL.md`	This documentation
`scripts/check-tools.sh`	Detect available tools
`scripts/run-analysis.sh`	General analysis wrapper with role-based config
`scripts/run-web-research.sh`	Gemini web research
`scripts/run-peer-check.sh`	Quick feedback via external model
`scripts/run-code-review.sh`	Independent scoring review (mandatory)
`prompts/CODE_REVIEWER_PROMPT.md`	100-point scoring rubric
`prompts/CHECKER_PROMPT.md`	Critical checker for debates

Best Practices

Prefer Codex - Better reasoning for code analysis
Use Gemini for web - Google search integration
Always capture output - Don't rely on stdout
Set timeouts - Prevent hanging
Check exit codes - Handle failures gracefully

third-party-call

Popularity

Invocation

Tool Access

Context Preview

Supporting Files

SKILL.md

Similar Skills

Help us improve

Help us improve

Find plugins for your project

third-party-call

Popularity

Invocation

Tool Access

Context Preview

Supporting Files

SKILL.md

Third-Party Call Skill

Purpose

Supported Tools

Scripts

Check Available Tools

Run Analysis (Codex/Claude)

Run Web Research (Gemini)

Run Peer Check

Run Code Review (Independent Scoring)

Role-Based Model Configuration

Prompts

Tool Configurations

Codex (Preferred for Analysis)

Claude (Fallback)

Gemini (Web Research)

Security Model

Use Cases

1. Peer Code Review (Phase 6.2)

2. Design Proposal (Research Phase)

3. Independent Analysis (Refinement Phase)

Error Handling

Timeout Configuration

Integration Points

Files in This Skill

Best Practices

Similar Skills

Help us improve

Third-Party Call Skill

Purpose

Supported Tools

Scripts

Check Available Tools

Run Analysis (Codex/Claude)

Run Web Research (Gemini)

Run Peer Check

Run Code Review (Independent Scoring)

Role-Based Model Configuration

Prompts

Tool Configurations

Codex (Preferred for Analysis)

Claude (Fallback)

Gemini (Web Research)

Security Model

Use Cases

1. Peer Code Review (Phase 6.2)

2. Design Proposal (Research Phase)

3. Independent Analysis (Refinement Phase)

Error Handling

Timeout Configuration

Integration Points

Files in This Skill

Best Practices