@frenchtoastman/oh-my-groundcontrol 0.0.7 → 0.0.8

package/README.md

@@ -56,9 +56,26 @@ https://raw.githubusercontent.com/frenchtoasters/oh-my-groundcontrol/refs/heads/
 
 ### Mission Control Standards Adherence
 
-Our planning, execution, and verification pipelines enforce protocols based on official NASA standards:
-- **[NASA-STD-8739.8B](https://standards.nasa.gov/system/files/tmp/NASA-STD-8739.8B.pdf)** (Software Assurance and Software Safety Standard): Ensures rigorous traceability, off-nominal scenario handling, and safety-critical QA paths during the Groundcontrol planning phase.
-- **[NASA-STD-7009B](https://standards.nasa.gov/sites/default/files/standards/NASA/B/1/NASA-STD-7009B-Final-3-5-2024.pdf)** (Standard for Models and Simulations): Required during complex system modeling to enforce credibility assessment before committing to architectural designs.
+Our planning, execution, and verification pipelines enforce protocols based on official NASA standards. We have synthesized these into four core **NASA Guardrails** for AI agent execution:
+
+1. **Destructive Pause (NASA-STD-8739.8B):** Stop and request explicit user confirmation before irreversible actions (e.g., force pushing, bulk deletions).
+2. **Pre-Flight Verification (NASA-HDBK-8739.19-3):** Always run linters and typechecks (`bun run check:ci`, `bun run typecheck`) to validate changes before concluding.
+3. **Atomic Checkpoints (NASA-HDBK-8739.18):** Commit stable states before initiating widespread refactors.
+4. **Escalation Protocol (NASA-STD-7009B):** If an automated check fails 3+ times, stop guessing and ask the user for guidance.
+
+#### Source Documentation
+The principles driving our agent behavior are extracted directly from the [NASA Technical Standards System](https://standards.nasa.gov):
+
+- [NASA-STD-7009B](https://standards.nasa.gov/standard/nasa/nasa-std-7009): Standard for Models and Simulations
+- [NASA-STD-8739.8B](https://standards.nasa.gov/standard/nasa/nasa-std-87398): Software Assurance and Software Safety Standard
+- [NASA-STD-5017B](https://standards.nasa.gov/standard/nasa/nasa-std-5017): Design and Development Requirements for Mechanisms
+- [NASA-HDBK-8739.18](https://standards.nasa.gov/standard/nasa/nasa-hdbk-873918): Software Engineering Handbook
+- [NASA-HDBK-8739.19-2](https://standards.nasa.gov/standard/nasa/nasa-hdbk-873919-2): Software Assurance Handbook
+- [NASA-HDBK-8739.19-3](https://standards.nasa.gov/standard/nasa/nasa-hdbk-873919-3): Software Measurement Handbook
+- [NASA-HDBK-8709.22](https://standards.nasa.gov/standard/nasa/nasa-hdbk-870922): Safety and Mission Assurance Acronyms, Abbreviations, and Definitions
+- [NASA-HDBK-8709.24](https://standards.nasa.gov/standard/nasa/nasa-hdbk-870924): Planetary Protection Handbook
+- [NASA-HDBK-1004](https://standards.nasa.gov/standard/nasa/nasa-hdbk-1004): Data Requirements Descriptions (DRDs) for Software
+- [NASA-HDBK-1009A](https://standards.nasa.gov/standard/nasa/nasa-hdbk-1009): Software Error Causes
 
 > *At mission control, ten specialized operators govern the success of every launch. Each holds authority over a critical telemetry system. Together they ensure mission success. Here, ten agents govern the craft of code.*
 

package/dist/index.js

@@ -18952,6 +18952,12 @@ var DESIGNER_PROMPT = `You are a Designer - a frontend UI/UX specialist who crea
 - Leverage component libraries where available
 - Prioritize visual excellence\u2014code perfection comes second
 
+**NASA Guardrails (High-Reliability Mode)**:
+- **Destructive Pause**: Stop and request explicit user confirmation before irreversible actions (e.g., force pushing, bulk deletions).
+- **Pre-Flight Verification**: Always run linters/typechecks (\`bun run check:ci\`, \`bun run typecheck\`) to validate changes before concluding.
+- **Atomic Checkpoints**: Commit stable states before initiating widespread refactors.
+- **Escalation Protocol**: If an automated check fails 3+ times, stop guessing and ask the user for guidance.
+
 ## Output Quality
 You're capable of extraordinary creative work. Commit fully to distinctive visions and show what's possible when breaking conventions thoughtfully.`;
 function createDesignerAgent(model, customPrompt, customAppendPrompt) {
@@ -19012,7 +19018,13 @@ Concise answer to the question
 **Constraints**:
 - READ-ONLY: Search and report, don't modify
 - Be exhaustive but concise
-- Include line numbers when relevant`;
+- Include line numbers when relevant
+
+**NASA Guardrails (High-Reliability Mode)**:
+- **Destructive Pause**: Stop and request explicit user confirmation before irreversible actions (e.g., force pushing, bulk deletions).
+- **Pre-Flight Verification**: Always run linters/typechecks (\`bun run check:ci\`, \`bun run typecheck\`) to validate changes before concluding.
+- **Atomic Checkpoints**: Commit stable states before initiating widespread refactors.
+- **Escalation Protocol**: If an automated check fails 3+ times, stop guessing and ask the user for guidance.`;
 function createExplorerAgent(model, customPrompt, customAppendPrompt) {
   let prompt = EXPLORER_PROMPT;
   if (customPrompt) {
@@ -19073,7 +19085,13 @@ No changes required
 <verification>
 - Tests passed: [not run - reason]
 - LSP diagnostics: [not run - reason]
-</verification>`;
+</verification>
+
+**NASA Guardrails (High-Reliability Mode)**:
+- **Destructive Pause**: Stop and request explicit user confirmation before irreversible actions (e.g., force pushing, bulk deletions).
+- **Pre-Flight Verification**: Always run linters/typechecks (\`bun run check:ci\`, \`bun run typecheck\`) to validate changes before concluding.
+- **Atomic Checkpoints**: Commit stable states before initiating widespread refactors.
+- **Escalation Protocol**: If an automated check fails 3+ times, stop guessing and ask the user for guidance.`;
 function createFixerAgent(model, customPrompt, customAppendPrompt) {
   let prompt = FIXER_PROMPT;
   if (customPrompt) {
@@ -20866,7 +20884,13 @@ var LIBRARIAN_PROMPT = `You are Librarian - a research specialist for codebases
 - Provide evidence-based answers with sources
 - Quote relevant code snippets
 - Link to official docs when available
-- Distinguish between official and community patterns`;
+- Distinguish between official and community patterns
+
+**NASA Guardrails (High-Reliability Mode)**:
+- **Destructive Pause**: Stop and request explicit user confirmation before irreversible actions (e.g., force pushing, bulk deletions).
+- **Pre-Flight Verification**: Always run linters/typechecks (\`bun run check:ci\`, \`bun run typecheck\`) to validate changes before concluding.
+- **Atomic Checkpoints**: Commit stable states before initiating widespread refactors.
+- **Escalation Protocol**: If an automated check fails 3+ times, stop guessing and ask the user for guidance.`;
 function createLibrarianAgent(model, customPrompt, customAppendPrompt) {
   let prompt = LIBRARIAN_PROMPT;
   if (customPrompt) {
@@ -20907,7 +20931,13 @@ var ORACLE_PROMPT = `You are Oracle - a strategic technical advisor.
 **Constraints**:
 - READ-ONLY: You advise, you don't implement
 - Focus on strategy, not execution
-- Point to specific files/lines when relevant`;
+- Point to specific files/lines when relevant
+
+**NASA Guardrails (High-Reliability Mode)**:
+- **Destructive Pause**: Stop and request explicit user confirmation before irreversible actions (e.g., force pushing, bulk deletions).
+- **Pre-Flight Verification**: Always run linters/typechecks (\`bun run check:ci\`, \`bun run typecheck\`) to validate changes before concluding.
+- **Atomic Checkpoints**: Commit stable states before initiating widespread refactors.
+- **Escalation Protocol**: If an automated check fails 3+ times, stop guessing and ask the user for guidance.`;
 function createOracleAgent(model, customPrompt, customAppendPrompt) {
   let prompt = ORACLE_PROMPT;
   if (customPrompt) {
@@ -21052,6 +21082,12 @@ Balance: respect dependencies, avoid parallelizing what must be sequential.
 - Confirm specialists completed successfully
 - Verify solution meets requirements
 
+## NASA Guardrails (High-Reliability Mode)
+1. **Destructive Pause:** Stop and request explicit user confirmation before irreversible actions (e.g., force pushing, bulk deletions).
+2. **Pre-Flight Verification:** Always run linters/typechecks (\`bun run check:ci\`, \`bun run typecheck\`) to validate changes before concluding.
+3. **Atomic Checkpoints:** Commit stable states before initiating widespread refactors.
+4. **Escalation Protocol:** If an automated check fails 3+ times, stop guessing and ask the user for guidance.
+
 ## Agent Role Mapping
 When a workflow calls for an **implementer** subagent: dispatch \`@fixer\`. Fixer has enforced constraints (no research, no delegation, structured output) that match the implementer role exactly.
 When a workflow calls for a **reviewer** subagent: dispatch \`@oracle\`. Oracle has the depth for architectural review and access to code review skills.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@frenchtoastman/oh-my-groundcontrol",
-  "version": "0.0.7",
+  "version": "0.0.8",
   "description": "Lightweight agent orchestration plugin for OpenCode - a slimmed-down fork of oh-my-opencode",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",