harness-engineering
Harness Engineering
Design the system around AI agents for reliable, safe production use.
Usage Template
Prompt
Use harness-engineering for this agent workflow. Design permissions, tools, feedback loops, observability, and failure handling.
Use Case
- Moving an agent workflow from ad hoc prompting toward a reliable runtime architecture.
Expected Result
- The agent produces a harness design with permission tiers, tool boundaries, logs, evals, and recovery paths.
Output Example
- A runtime spec with permission matrix, tool allowlist, approval gates, logs, evals, and incident response.
More from mark393295827/third-brain-v5-skills
project-flow-ops
Operate execution flow — triage tasks, manage priorities, keep progress structured. Use when the user needs backlog control, task planning, or workflow coordination across projects.
2context-manager
Manage the LLM's context window — token budgeting, prompt assembly, truncation strategies. Use when approaching context limits or optimizing prompt costs.
2deep-research
Multi-source deep research — search, synthesize, and deliver cited reports. Use when the user wants thorough research on any topic with evidence and citations.
2verify-before-claim
Iron rule — no completion claims without fresh verification evidence. Use whenever about to claim work is done, fixed, working, or passing. Run verification commands and show output before making any success statement.
2wiki-lint
Health-check the knowledge wiki — find orphans, broken links, missing frontmatter, contradictions, stale content, and statistical drift. Use when the user says "lint the wiki", "health check", or periodically for maintenance.
1daily-okr
Execute a daily knowledge compound closed loop — 7 Key Results from input to feedback with scoring. Use when the user wants to do a daily review, plan their day, or run a knowledge workflow.
1