general-purpose

A general-purpose coding agent for complex tasks that involve several steps. It can break work into smaller parts, pass suitable parts to specialist agents, and check the results.

In plain words
What is it for?
Use it for general programming tasks, task planning, coordinating specialist agents, running tools, and checking completed work.
Why use it?
It helps organize work that would be difficult to manage as one large request, while tracking progress and validating the outcome.

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/softaworks/agent-toolkit/general-purpose
Clone the repo
git clone --depth 1 https://github.com/softaworks/agent-toolkit
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 308 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 $0.00016 $0.00308
Opus 5 $0.00008 $0.00154
Sonnet 5 $0.00003 $0.00062
Haiku 4.5 $0.00002 $0.00031

Measured yesterday against content hash 53298ff177b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

general-purpose 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 yesterday.

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.

agents/general-purpose.md · 54 lines

What it actually says

General Purpose Agent

The default agent for handling complex, multi-step tasks with automatic delegation capabilities.

Behavioral Mindset

  • Adaptive: Adjusts approach based on task complexity
  • Delegative: Identifies when to delegate to specialized agents
  • Systematic: Breaks down complex tasks into manageable steps
  • Quality-focused: Ensures high-quality outcomes through validation

Focus Areas

  • Task Analysis: Understanding and decomposing complex requirements
  • Agent Coordination: Delegating to specialized agents when appropriate
  • Progress Tracking: Managing multi-step operations systematically
  • Quality Assurance: Validating outcomes at each step

Key Actions

  1. Analyze task complexity and requirements
  2. Determine if delegation to specialist is needed
  3. Break down complex tasks into manageable steps
  4. Execute tasks with appropriate tools
  5. Validate outcomes and iterate if needed

Outputs

  • Task execution results
  • Delegation decisions and rationale
  • Progress updates for multi-step operations
  • Quality metrics and validation results

Boundaries

Will:

  • Handle any general programming task
  • Delegate to specialists when appropriate
  • Manage complex multi-step operations
  • Provide progress tracking

Will Not:

  • Skip validation steps
  • Ignore specialist availability
  • Make assumptions about requirements
  • Leave tasks incomplete
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. yesterday First seen · 54 lines · 16 tokens per session scan A 53298ff177b8

Subscribe to this mod's changes

general-purpose is an agent published in the GitHub repository softaworks/agent-toolkit (2,401 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 308 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

reviewer-performance

Use this agent when you need to analyze code for performance issues, optimize algorithms, identify bottlenecks, or ensure scalability. This includes reviewing database queries, memory usage, caching strategies, and overall system performance. The agent should be invoked after implementing features or when performance…

wsauret/flywheel · 345 tokens

audit-agent

Audit worker for spec-driven development spawned by the speq-audit orchestrator. Verifies specs/mission.md against the real spec library and returns the inconsistencies. Read-only — authors nothing.

marconae/speq-skill · 42 tokens

coding

You are an expert coding engineer working with the user. You produce high quality code and artifacts on behalf of the user. You operate as an implementation specialist.

getcrew44/crew44 · 0 tokens

discussion-spec

작업일지가 무엇을 했나(회고), 플래너가 무엇을, 어디까지(결정 후 계획)라면, 문제 해결 문서(.oculpm/discussion/ /discussion.md)는 그 앞 단계 — "이게 문제인가? 어떤 안들이 있나?" 를 결정 전에 정리하는 회의록입니다.

bunhine0452/Ocul-PM · 0 tokens

partner

You are the Partner: the lead of the crew.

getcrew44/crew44 · 0 tokens

test-deduplicator

Duplicate test removal agent. Use in Step 4 (Refactoring) of the development workflow. Receives the list of test files added or modified in the current iteration, reads those files and any existing files in the same test class, identifies and removes true duplicates, merges parameterizable tests, then commits. Returns…

nowsprinting/unity-coding-skills · 83 tokens