Install
$ agentstack add skill-osovv-grace-marketplace-grace-init ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Initialize GRACE framework structure for this project.
Template Files
All documents MUST be created from template files located in this skill's assets/ directory. Read each template file, replace the $PLACEHOLDER variables with actual values gathered from the user, and write the result to the target project path.
| Template source | Target in project | |------------------------------------------|-----------------------------| | assets/AGENTS.md.template | AGENTS.md (project root) | | assets/docs/knowledge-graph.xml.template | docs/knowledge-graph.xml | | assets/docs/requirements.xml.template | docs/requirements.xml | | assets/docs/technology.xml.template | docs/technology.xml | | assets/docs/development-plan.xml.template| docs/development-plan.xml | | assets/docs/verification-plan.xml.template| docs/verification-plan.xml | | assets/docs/operational-packets.xml.template| docs/operational-packets.xml |
> Important: Never hardcode template content inline. Always read from the .template files — they are the single source of truth for document structure.
Steps
- Gather project info from the user. Ask for:
- Project name and short annotation
- Main keywords (for domain activation)
- Primary language, runtime, and framework (with versions)
- Key libraries/dependencies (if known)
- Testing stack (test runner, assertion style, mock/fake approach)
- Observability stack (logger, structured log fields, redaction constraints)
- High-level module list (if known)
- 2-5 critical flows or risky surfaces that must be verifiable early
- Create
docs/directory and populate documents from templates:
For each assets/docs/*.xml.template file:
- Read the template file
- Replace
$PLACEHOLDERvariables with user-provided values - Write the result to the corresponding
docs/path
- Create or verify
AGENTS.mdat project root:
- If
AGENTS.mddoes not exist — readassets/AGENTS.md.template, fill in$KEYWORDSand$ANNOTATION, and write to project root - If
AGENTS.mdalready exists — warn the user and ask whether to overwrite or keep the existing one
- Print a summary of all created files and suggest the next step:
> "Run $grace-plan to design modules, data flows, and verification references. Then use $grace-verification to deepen tests, traces, and log-driven evidence before large execution waves. Use docs/operational-packets.xml as the canonical packet and delta reference during execution and refactors."
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: osovv
- Source: osovv/grace-marketplace
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.