im-shashanks/claude-plugins / shaktra/skills/shaktra-reference
shaktra-reference
VerifiedShared constants, quality standards, and state schemas for all Shaktra agents. Defines severity taxonomy, quality principles, guard tokens, review dimensions, and YAML schemas.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 4.0 KB |
| guard-tokens.md | markdown | 3.0 KB |
| quality-dimensions.md | markdown | 4.0 KB |
| quality-principles.md | markdown | 3.9 KB |
| schemas/analysis-manifest-schema.md | markdown | 2.8 KB |
| schemas/anti-patterns-schema.md | markdown | 1.6 KB |
| schemas/briefing-schema.md | markdown | 2.9 KB |
| schemas/design-doc-schema.md | markdown | 4.9 KB |
| schemas/handoff-schema.md | markdown | 4.2 KB |
| schemas/journey-schema.md | markdown | 3.4 KB |
| schemas/observations-schema.md | markdown | 1.7 KB |
| schemas/persona-schema.md | markdown | 2.8 KB |
| schemas/prd-schema.md | markdown | 3.3 KB |
| schemas/principles-schema.md | markdown | 2.3 KB |
| schemas/procedures-schema.md | markdown | 1.7 KB |
| schemas/refactoring-handoff-schema.md | markdown | 2.4 KB |
| schemas/research-schema.md | markdown | 3.7 KB |
| schemas/settings-schema.md | markdown | 7.7 KB |
| severity-taxonomy.md | markdown | 3.2 KB |
guard-tokens.md
View on GitHub# Guard Tokens
14 core workflow tokens used for signaling across Shaktra agents. Tokens are emitted as plain text markers in agent output. Domain-specific skills define additional tokens (review: 4, analyze: 3, general: 3, bugfix: 3, refactoring: 2) in their respective SKILL.md files.
## Phase Progression
| Token | When Emitted | Emitter | What Happens Next |
|---|---|---|---|
| `TESTS_NOT_RED` | Test suite does not have a failing test before implementation begins | Orchestrator, Test Agent | Block implementation — write a failing test first |
| `TESTS_NOT_GREEN` | Implementation complete but tests still failing | Developer | Return to implementation — fix until tests pass |
| `PHASE_GATE_FAILED` | A TDD phase transition check failed (red/green/refactor) | SW Quality | Block phase transition — resolve the failure |
| `COVERAGE_GATE_FAILED` | Coverage falls below the tier's required threshold | Developer, SW Quality | Block completion — add tests to meet threshold |
## Quality Gates
| Token | When Emitted | Emitter | What Happens Next |
|---|---|---|---|
| `CHECK_PASSED` | A quality check passed during development | SW Quality | Continue to next check or phase |
| `CHECK_BLOCKED` | A quality check failed during the TDD fix loop | SW Quality | Return to fix loop — address the finding |
| `QUALITY_PASS` | Quality gate passed (0 P0, P1 within threshold) | SW Quality, TPM Quality | Proceed to next phase or allow merge |
| `QUALITY_BLOCKED` | Quality gate failed (P0 exists or P1 exceeds threshold) | SW Quality, TPM Quality | Block — resolve findings first |
| `REFACTOR_PASS` | Refactoring verification passed — behavior preserved, metrics improved | SW Quality | Proceed to completion |
| `REFACTOR_BLOCKED` | Refactoring verification failed — tests broken, coverage decreased, or P0/P1 found | SW Quality | Return to fix loop — address regressions |
| `ADVERSARIAL_PASS` | Adversarial review passed — mutation score above threshold, no P0, P1 within limit | Adversarial Review | Proceed with confidence |
| `ADVERSARIAL_CONCERN` | Mutation score below threshold or significant blind spots found | Adversarial Review | Review blind spots — merge with awareness |
| `ADVERSARIAL_BLOCKED` | P0 findings from adversarial testing | Adversarial Review | Fix critical issues before merge |
## Workflow
| Token | When Emitted | Emitter | What Happens Next |
|---|---|---|---|
| `MAX_LOOPS_REACHED` | A fix/retry loop hit its iteration cap without resolution | Any Agent | Stop loop, escalate to user with findings |
## Communication
| Token | When Emitted | Emitter | What Happens Next |
|---|---|---|---|
| `GAPS_FOUND` | Story or design has gaps that must be filled before work begins | Architect, TPM Quality | Return to planning — fill gaps before proceeding |
| `CLARIFICATION_NEEDED` | Ambiguity that cannot be resolved from available context | Any Agent | Ask user for clarification |
| `VALIDATION_FAILED` | Schema or state file validation failed | Any Agent | Report invalid fields, block until corrected |
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |