Grace execute
GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.
npx -y skills add osovv/grace-marketplace --skill grace-executeAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Execute an approved GRACE 4 GraceChangePlan in sequential or parallel-safe mode with recovery-aware preflight and centralized durable apply.
SKILL.md
2.9 KB, as published. Nobody here has run it
<assertion_commands>
- Current validation:
grace lint --path PROJECT --assertions current - Selected baseline:
grace lint --path PROJECT --change C-ID --assertions baseline(add--run-commandswhen the baseline declaresMustPassCommand) - Selected target without commands:
grace lint --path PROJECT --change C-ID --assertions target - Selected target with command evidence:
grace lint --path PROJECT --change C-ID --assertions target --run-commands - Final end-state validation:
grace lint --path PROJECT --change C-ID --assertions final(add--run-commandswhen the target declaresMustPassCommand) - Parallel preflight:
grace lint --path PROJECT --parallel-preflight</assertion_commands>
<mode_selection>
Wait for explicit sequential or parallel-safe choice. Parallel-safe requires the explicit preflight to pass. Workers never mutate approved plans; durable .grace changes are applied centrally after observed work verifies.
</mode_selection>
<recovery_decision_table> | state | required action | | clean-to-start | Run selected baseline, then execute tasks. | | partial-observed-writes | Inspect the declared observed scope and ask whether to resume or revert. | | durable-state-changed | Hard stop; supersede and replan. Approved assertions are immutable. | | target-already-satisfied | Run final end-state validation, opted-in command evidence when declared, durable reconciliation, and ask for explicit apply confirmation. | | unsafe-unknown-drift | Hard stop and report unexplained files. | </recovery_decision_table>
<execution_rules>
- Run the selected baseline before implementation, including explicit
--run-commandswhen its assertions declareMustPassCommand. - Execute one dependency-ready task or one verified parallel-safe batch at a time.
- Run each task's acceptance and verification immediately.
- Apply approved durable context, graph, and verification changes centrally.
- Reconcile durable state, run plan gates, then run selected
--assertions final, including--run-commandswhenMustPassCommandis declared. Final mode performs full project lint, evaluates the selected target, keeps unrelated approved baselines active, and does not re-evaluate the selected plan's superseded baseline. - Ask for explicit apply confirmation after fresh end-state evidence passes.
- Only then set spec and plan to
appliedand archive the complete bundle. - Never edit approved assertions/scopes/tasks in place, bypass stale evidence, or continue through unknown drift. </execution_rules> </skill>