Grace setup subagents

Skill osovv/grace-marketplace/skills/grace/grace-setup-subagents

Create GRACE 4 worker and reviewer subagent presets that understand .grace artifacts, scopes, assertions, and verification evidence.From its SKILL.md

Install

npx -y skills add osovv/grace-marketplace --skill grace-setup-subagents

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

0.7 KB, 117 tokens by cl100k_base, as published. Nobody here has run it

<skill> <subagent_requirements> Generated subagents must be told to:

read .grace/context, .grace/graph, .grace/verification, and relevant .grace/changes packets explicitly;
treat spec.xml as normative and design context as non-normative;
respect DurableScope, ObservedWriteScope, BaselineAssertions, and TargetAssertions;
never mutate approved plans or XML statuses without controller approval;
return verification evidence and scoped graph/verification deltas. </subagent_requirements> </skill>

What ships with it: 5 files

6.6 KB alongside SKILL.md

agents/

openai.yaml136 B

references/

Gives 0 of the 12 instructions most project setup skills give in 117 tokens

Counted across 1,553 of the 3,091 authors here whose files we hold, read 2026-09-06

Write the configuration filein 36 of 1553
Create the directory structurein 35 of 1553, across 33 files
Verify the setupin 31 of 1553, across 28 files
Run the setup scriptin 30 of 1553, across 29 files
Pre-determine the required sample sizein 29 of 1553, across 12 files
Check if the configuration already existsin 29 of 1553
Document every testin 26 of 1553, across 10 files
Start with a hypothesisin 26 of 1553, across 11 files
Ask one question at a timein 22 of 1553
Test a single variable per testin 21 of 1553, across 9 files
Read product marketing context before asking questionsin 19 of 1553, across 8 files
Do not peek and stop earlyin 18 of 1553, across 7 files

Said here and by no other author read

Read grace context and graph packets explicitly
Treat spec xml as normative
Respect durable and observed write scopes
Respect baseline and target assertions
Return verification evidence and scoped deltas

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.