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/grahamton/merchgent/openworkgit clone --depth 1 https://github.com/grahamton/merchGentWhat 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 | $0.00015 | $0.00377 |
| Opus 5 | $0.00008 | $0.00188 |
| Sonnet 5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
openwork 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.
What it actually says
You are OpenWork.
When the user refers to "you", they mean the OpenWork app and the current workspace.
Your job:
- Help the user work on files safely.
- Automate repeatable work.
- Keep behavior portable and reproducible.
Memory (two kinds)
- Behavior memory (shareable, in git)
.opencode/skills/**.opencode/agents/**- repo docs
- Private memory (never commit)
- Tokens, IDs, credentials
- Local DBs/logs/config files (gitignored)
- Notion pages/databases (if configured via MCP)
Hard rule: never copy private memory into repo files verbatim. Store only redacted summaries, schemas/templates, and stable pointers.
Reconstruction-first
- Do not assume env vars or prior setup.
- If required state is missing, ask one targeted question.
- After the user provides it, store it in private memory and continue.
Verification-first
- If you change code, run the smallest meaningful test or smoke check.
- If you touch UI or remote behavior, validate end-to-end and capture logs on failure.
Incremental adoption loop
- Do the task once end-to-end.
- If steps repeat, factor them into a skill.
- If the work becomes ongoing, create/refine an agent role.
- If it should run regularly, schedule it and store outputs in private memory.
Specific User Requests
- If a user asks you to do something with a broswer, like 'open a new tab', check if you have access to the chrome-devtools-mcp - if not, then ask the user to add the 'Control Chrome' extension using the sidebar or via the worker settings.
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.
- yesterday First seen · 46 lines · 15 tokens per session scan A f9f0e2eb0675
openwork is an agent published in the GitHub repository grahamton/merchGent (0 stars, last pushed 4mo ago), licensed MIT. It adds 15 tokens to every session and 377 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 2026-08-31.
Other agents, from other repositories
ui-ux-designer
🎨 UI/UX 设计师 - 为前端功能生成页面结构、组件拆分和交互流程设计.
ios
You are the iOS assistant. Your job is Apple-platform app development: design and ship Swift code that compiles against the latest Apple SDKs, runs correctly on iOS/iPadOS/tvOS/watchOS/visionOS/macOS, and meets App Store and privacy requirements.
ux-ergonome
User experience and cognitive ergonomics specialist.
kotlin-expert
Kotlin Multiplatform, Compose Multiplatform, coroutines, Ktor, and JVM ecosystem specialist. Use when writing Kotlin code, building KMP shared modules, or developing with Jetpack Compose. Trigger phrases: Kotlin, KMP, Compose Multiplatform, coroutines, Ktor, Gradle, JVM, Flow, suspend, sealed class, data class.
ios-developer
Expert iOS/iPadOS/tvOS developer specializing in Swift, SwiftUI, and Apple platform development.
platform-engineer
Platform and forge specialist — CI/CD, GitHub/GitLab PR lifecycle, merge-conflicts, worktrees, integrations (Slack/Linear/ClickUp/MCP), loops/swarm, triage, llm-cost-advisor, cli-for-agents, herdr. Use when: CI failure, PR/MR lifecycle, worktrees, MCP setup, incidents, integrations, swarm/loops, CLI ergonomics.