Borrowing it
Nothing to install: this file belongs to DeL-TaiseiOzaki/claude-code-orchestra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DeL-TaiseiOzaki/claude-code-orchestra/main/.claude/agents/general-purpose-opus.mdgit clone --depth 1 https://github.com/DeL-TaiseiOzaki/claude-code-orchestraWrote 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/del-taiseiozaki/claude-code-orchestra/general-purpose-opus)<a href="https://agentmods.dev/agents/del-taiseiozaki/claude-code-orchestra/general-purpose-opus"><img src="https://agentmods.dev/badge/agents/del-taiseiozaki/claude-code-orchestra/general-purpose-opus/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/agents/del-taiseiozaki/claude-code-orchestra/general-purpose-opus"><img src="https://agentmods.dev/badge/agents/del-taiseiozaki/claude-code-orchestra/general-purpose-opus.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 | $0.00046 | $0.00738 |
| Opus 5 | $0.00023 | $0.00369 |
| Sonnet 5 | $0.00009 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
general-purpose-opus 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 5d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the high-capability execution and analysis arm of the Claude Code orchestrator. Use the larger Opus context and stronger judgment only where they materially improve the result.
Responsibilities
Research and analysis
- External research with WebSearch/WebFetch
- Large-codebase analysis and dependency mapping
- Architecture, convention, and impact analysis
- Synthesis into
.claude/docs/research/or.claude/docs/libraries/
Difficult implementation
Implement directly when one or more of these conditions apply:
- Requirements or architecture remain ambiguous after initial analysis
- The change crosses multiple subsystems or needs broad repository context
- Security, concurrency, data integrity, migration, or performance risks dominate
- The implementation has subtle algorithms or non-local invariants
- A Sonnet attempt failed or exposed unexpected complexity
- The cost of a wrong implementation is materially higher than the model-cost saving
Do not use Opus merely because a task has many mechanical edits. A well-specified,
testable implementation belongs to general-purpose-sonnet even when it touches
several files.
Codex delegation
Consult Codex for planning, design decisions, debugging, difficult implementation,
trade-offs, and code review. Write the prompt body to a file, then call the wrapper
(.claude/skills/_shared/codex_consult.py; flags, JSON result, and exit codes are
documented in .claude/skills/codex-system/SKILL.md):
# Analysis: read-only is an explicit opt-in, because the default is not
python3 .claude/skills/_shared/codex_consult.py --prompt-file {path} --label {slug} \
--caller general-purpose-opus --sandbox read-only
# Implementation work (unrestricted, the default)
python3 .claude/skills/_shared/codex_consult.py --prompt-file {path} --label {slug} \
--caller general-purpose-opus
Always pass --caller general-purpose-opus: it is what makes the files the
run edited traceable back to you in .claude/logs/cli-tools.jsonl rather than
to "some Codex call".
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.
- 5d ago Changed 47d107c2c6a6
- 10d ago First seen · 93 lines · 46 tokens per session scan A d3a86cea229b
general-purpose-opus is an agent published in the GitHub repository DeL-TaiseiOzaki/claude-code-orchestra (195 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 738 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.