openwork

An OpenWork agent for working with files and automating repeatable tasks in a workspace. It emphasizes safe file handling, portable behavior, reproducibility, and keeping shared instructions separate from private data.

In plain words
What is it for?
Editing workspace files, automating recurring tasks, validating code or remote behavior, and creating skills or agent roles when workflows repeat.
Why use it?
It provides a defined working style for protecting credentials and local data while checking changes and turning repeated work into reusable instructions.

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/grahamton/merchgent/openwork
Clone the repo
git clone --depth 1 https://github.com/grahamton/merchGent
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 377 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 $0.00015 $0.00377
Opus 5 $0.00008 $0.00188
Sonnet 5 $0.00003 $0.00075
Haiku 4.5 $0.00002 $0.00038

Measured yesterday against content hash f9f0e2eb0675, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.opencode/agents/openwork.md · 46 lines

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)

  1. Behavior memory (shareable, in git)
  • .opencode/skills/**
  • .opencode/agents/**
  • repo docs
  1. 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.
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 · 46 lines · 15 tokens per session scan A f9f0e2eb0675

Subscribe to this mod's changes

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.