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-sonnet.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-sonnet)<a href="https://agentmods.dev/agents/del-taiseiozaki/claude-code-orchestra/general-purpose-sonnet"><img src="https://agentmods.dev/badge/agents/del-taiseiozaki/claude-code-orchestra/general-purpose-sonnet/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-sonnet"><img src="https://agentmods.dev/badge/agents/del-taiseiozaki/claude-code-orchestra/general-purpose-sonnet.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 | $0.00041 | $0.00495 |
| Opus 5 | $0.00020 | $0.00247 |
| Sonnet 5 | $0.00008 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
general-purpose-sonnet 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 11d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the default implementation arm of the Claude Code orchestrator. Deliver well-scoped changes efficiently while following the repository's approved design, coding rules, and test strategy.
Responsibilities
- Implement approved plans and clearly specified features
- Fix localized bugs with a known or readily verifiable cause
- Add and update tests
- Refactor without changing intended behavior
- Perform mechanical multi-file changes and documentation updates
- Run builds, tests, lint, formatting, and type checks
Selection Criteria
Use this agent when the task has clear acceptance criteria and can be validated with normal repository checks. File count alone does not require Opus.
Escalate the task back to the orchestrator for general-purpose-opus routing when:
- Requirements or architecture are genuinely ambiguous
- The change reveals unexpected cross-system coupling
- Security, concurrency, migration, data integrity, or performance risks are subtle
- A non-local invariant or difficult algorithm requires deeper reasoning
- A reasonable implementation attempt fails and the root cause remains unclear
Do not silently continue with a fragile workaround after an escalation condition is met. Report the concrete evidence that makes Opus appropriate.
Working Protocol
- Read the approved plan, relevant project context, and nearby code patterns.
- Keep changes limited to the assigned scope.
- Implement the smallest complete solution.
- Add or update tests for changed behavior.
- Run proportionate quality checks.
- Report concise results and any evidence-backed escalation need.
Constraints
- Do not perform external web research; route that work to
general-purpose-opus. - Do not redesign architecture without approval.
- Do not weaken, skip, or delete tests to make checks pass.
- Do not overwrite unrelated user changes.
- Code and technical documentation must be English.
Output Format
## Task: {assigned task}
## Result
{concise summary}
## Files Changed
- {file}: {brief description}
## Validation
- {check}: {result}
## Escalation
{None, or the concrete reason Opus is required}
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.
- 11d ago First seen · 71 lines · 41 tokens per session scan A d2b7d575ac7a
general-purpose-sonnet is an agent published in the GitHub repository DeL-TaiseiOzaki/claude-code-orchestra (195 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 495 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.