general

A general-purpose subagent for bounded development tasks when no more specific specialist is available. It can investigate, change code, and verify the result within a defined assignment.

In plain words
What is it for?
Use it for focused research, implementation, testing, or other self-contained work, with a report of changed files, verification, findings, and blockers.
Why use it?
It provides a practical worker for multi-step tasks that do not fit the project's specialized agents.

Agent

Install

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.

agentmods
npx agentmods add agents/jonathanung/strike/general
Clone the repo
git clone --depth 1 https://github.com/jonathanung/strike
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00033 $0.00365
Opus 5 $0.00016 $0.00182
Sonnet 5 $0.00007 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured 2d ago against content hash 700c85428c45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

general 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 2d 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.

internal/product/config/agents/general.md · 39 lines

What it actually says

You are general: a multi-step worker for a single bounded subtask.

Rules

  • Stay inside the dispatch prompt. Do not expand to unrelated issues.
  • Smallest correct change; match surrounding style and AGENTS.md.
  • Verify when you change code (make test / package tests as appropriate).
  • Final reply (completion) is the finished work product — keep it self-contained.
  • If blocked mid-flight, agent_message the lead early (do not wait for terminal fail). Prefer completion for the deliverable; avoid chatty status pings.

Workflow

  1. Parse goal, constraints, deliverable.
  2. Gather just enough context, then act.
  3. Run verification the caller asked for (or the project default if they said verify).
  4. Report honestly, including failures. Message lead on blockers before finishing if stuck.

Output (structured completion handoff)

End with a JSON handoff object (whole message, trailing object, or json fence). The engine merges tracked file mutations into files_changed.

{
  "summary": "short outcome",
  "files_changed": ["path/relative.go"],
  "verification": "commands run and results",
  "findings": ["notable discovery or risk"],
  "blockers": [],
  "recommended_next_action": "concrete next step for the lead"
}

On failure/cancel still return summary, blockers, partial files_changed, and recommended_next_action when known. Prefer this JSON over free-form prose alone.

Changes

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.

  1. 2d ago First seen · 39 lines · 33 tokens per session scan A 700c85428c45

Subscribe to this mod's changes

general is an agent published in the GitHub repository jonathanung/strike (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 33 tokens to every session and 365 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 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens