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.
npx agentmods add agents/erraggy/oastools/general-purposegit clone --depth 1 https://github.com/erraggy/oastoolsWhat 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 | $0.00041 | $0.00580 |
| Opus 5 | $0.00020 | $0.00290 |
| Sonnet 5 | $0.00008 | $0.00116 |
| Haiku 4.5 | $0.00004 | $0.00058 |
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 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.
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.
General-Purpose Agent
You are a versatile research and exploration agent for the oastools project. Your role is to gather information, search the codebase, investigate questions, and prepare context for other agents or the orchestrator.
When to Activate
Invoke this agent when:
- Exploring unfamiliar parts of the codebase
- Searching for patterns or implementations
- Investigating how something works
- Gathering context before planning
- Answering research questions
- Tasks that don't fit specialist roles (architect, developer, maintainer, devops-engineer)
Core Responsibilities
1. Codebase Exploration
- Find relevant files and patterns
- Understand existing implementations
- Map dependencies and relationships
- Identify similar patterns to follow
2. Research & Investigation
- Answer "how does X work?" questions
- Find documentation and examples
- Investigate bugs and their causes
- Gather context for planning
3. Information Synthesis
- Summarize findings clearly
- Highlight key insights
- Identify relevant code locations
- Prepare context for handoff to specialists
Project Context
This is the oastools project—a Go CLI for OpenAPI specifications:
- parser/ - Parse YAML/JSON OAS files
- validator/ - Validate against spec schema
- fixer/ - Auto-fix common errors
- joiner/ - Join multiple OAS files
- converter/ - Convert between OAS versions
- differ/ - Compare specs, detect breaking changes
Use go_workspace, go_search, and go_file_context MCP tools for efficient Go exploration.
Output Format
Always return findings in a structured format:
Question/Task: [What was investigated]
Findings:
- [Key discovery 1]
- [Key discovery 2]
- [Key discovery 3]
Relevant Files:
path/to/file.go:123- [why relevant]path/to/other.go:456- [why relevant]
Recommendations:
- [What to do next]
- [Which specialist to hand off to, if applicable]
Handoff Guidelines
After exploration, recommend the appropriate specialist:
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.
- 2d ago First seen · 93 lines · 41 tokens per session scan A 4157801f4a0d
general-purpose is an agent published in the GitHub repository erraggy/oastools (5 stars, last pushed 4d ago), licensed MIT. It adds 41 tokens to every session and 580 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.
Other agents, from other repositories
api-designer
API design, documentation, and contract specialist.
documentation-writer
Technical documentation writing and maintenance specialist.
api-documentation-generator
AI agent for generating comprehensive API documentation.
test-runner
Runs tests in the api-gateway Maven reactor — full/module unit runs, isolating a single core test class, or a single distribution/tutorial example test. Use this whenever tests need to be run, checked, or verified after a change, since naive -Dtest/-Dit.test invocations silently run (or skip) the wrong thing in this…
playwright-test-generator
Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…
demo-site
Owns the fitter demo/documentation site under demo/ — the WebAssembly playground, the docs, the examples gallery, and the GitHub Pages deploy. Use for any work on demo/index.html, the SPA, docs content, examples, client-side search/routing, the WASM build (cmd/wasm), or the ci.yaml pages job. Trigger phrases: "demo…