agent-debug
starsforks
How to install agent-debug?
rlaope/oh-my-hermes/agent-debug
$npx -y skills add rlaope/oh-my-hermes --skill agent-debug[omh] Agent Debug workflow: capture a stuck, looping, drifting, or repeatedly failing agent run, diagnose the likely failure pattern, and prepare the smallest safe recovery action.
SKILL.md
| 1 | # Agent Debug |
| 2 | |
| 3 | This is a Hermes-native `agent-debug` workflow skill. |
| 4 | |
| 5 | ## Why This Exists |
| 6 | |
| 7 | `agent-debug` exists so Hermes users can ask for this workflow in chat and receive a structured, evidence-bounded OMH operating surface instead of ad hoc narration. |
| 8 | |
| 9 | ## Do Not Use When |
| 10 | |
| 11 | - The request is already handled by a narrower explicit skill with stronger evidence. |
| 12 | - The user asks OMH to secretly run external platforms, connectors, schedulers, file exports, or runtime agents. |
| 13 | - The only safe answer is to ask for missing authority, credentials, target, or observed evidence first. |
| 14 | |
| 15 | ## Examples |
| 16 | |
| 17 | Good example: |
| 18 | |
| 19 | - Prompt: agent-debug capture why this agent is looping on the same tool and prepare the smallest safe recovery action. |
| 20 | - Expected behavior: Produce `prepare_agent_debug` with required context, wrapper actions, and not-evidence boundaries. |
| 21 | - Why: The prompt names a real workflow surface that Hermes can orchestrate without hiding execution. |
| 22 | |
| 23 | Bad example: |
| 24 | |
| 25 | - Prompt: agent-debug silently reset the executor, patch the environment, and claim the future loop is fixed. |
| 26 | - Expected behavior: Report the missing observed evidence or authority instead of claiming the external step happened. |
| 27 | - Why: Prepared OMH guidance is not platform, runtime, connector, file, memory, or delivery evidence. |
| 28 | |
| 29 | ## Completion Checklist |
| 30 | |
| 31 | - Failure state, intended goal, recent tool sequence, and context pressure are captured. |
| 32 | - Diagnosis distinguishes repeated command/tool loops, context drift, environment mismatch, service errors, and wrong-hypothesis tests. |
| 33 | - Recovery action is contained, reversible, and does not claim implementation, verification, CI, merge, or future-loop fixes. |
| 34 | |
| 35 | ## Recovery Notes |
| 36 | |
| 37 | - If the request is install/setup health, route to doctor. |
| 38 | - If the request is a manager status or throughput review, route to agent-ops-review. |
| 39 | - If the request is a durable self-improvement record after diagnosis, route to workflow-learning. |
| 40 | |
| 41 | ## OMH Context Rail |
| 42 | |
| 43 | - This skill is part of OMH's Hermes workflow layer, not a standalone executor. |
| 44 | - Product context: OMH is a Hermes-native workflow pack: choose skills, shape work, prepare artifacts, show status, and hand off with evidence boundaries. |
| 45 | - Current lane: **Automation and status** (`achievements`, `workspace-audit`, `production-audit`, `automation-blueprint`, `github-event-ops`, `agent-board`, `gateway-intent-card`, `voice-operator`, `+26 more`) - schedules, status, health, and ops review. |
| 46 | - If the user intent belongs to another OMH lane, hand back to `oh-my-hermes` or name the adjacent workflow instead of force-fitting this skill. |
| 47 | - Cross-skill context: every OMH skill: match lane; generic tool can render or execute. |
| 48 | - Generic-tool checkpoint: image->img-summary; frontend->frontend/a11y/visual-qa; paper->paper-learning; content->content-operator; media->media-input-operator; file->materials-package; search->web-research; live->live-info-operator; audit->workspace/production/security; failures->build-failure; verify->verification-gate; code->codegraph/onboarding/ultraprocess. |
| 49 | - Coverage: Every generated workflow skill carries this rail. |
| 50 | - Normal users talk to Hermes; OMH CLI is infra. |
| 51 | - Boundary: Prepared OMH routing, cards, handoffs, or artifacts are not observed execution, image generation, delivery, review, CI, merge-readiness, or merge evidence. |
| 52 | |
| 53 | ## Use When |
| 54 | |
| 55 | Use when an agent run is stuck, looping on tools, burning tokens without progress, drifting from the objective, losing context, or failing on recoverable environment/tool assumptions. |
| 56 | |
| 57 | Strong routing signals: `agent-debug`, `agent debug`, `agent debugging`, `agent introspection`, `agent self-debug`, `self-debug`, `self debugging`, `looping agent`, `agent loop failure`, `agent run stuck`, `agent failure capture`, `tool retry loop`, `repeated tool calls`, `context drift`, `prompt drift`, `token burn`, `에이전트 디버그`, `에이전트 실패`, `에이전트 반복 실패`, `반복 실패`, `도구 반복`, `컨텍스트 드리프트`, `토큰 낭비` |
| 58 | |
| 59 | ## Catalog Metadata |
| 60 | |
| 61 | Category: `operations` |
| 62 | Phase: `agent-debug` |
| 63 | Hermes role: `operator` |
| 64 | Quality tier: `workflow-surface-gated` |
| 65 | |
| 66 | Quality bar: |
| 67 | |
| 68 | - Name the user-facing workflow objective, required context, next action, and stop condition. |
| 69 | - Separate prepared guidance from observed platform, runtime, connector, file, memory, or delivery evidence. |
| 70 | - Expose missing tools, credentials, targets, or observations as user-visible gaps. |
| 71 | |
| 72 | Handoff policy: |
| 73 | |
| 74 | Keep this as Hermes-facing orchestration guidance first. Prepare executor, connector, gateway, or host-runtime handoff only when the user accepts that next step and observed evidence can be recorded. |
| 75 | |
| 76 | Required inputs: |
| 77 | |
| 78 | - user req |
People who liked this also viewed
6 picksType
- azure-diagnosticsDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deploySkillsJul 2026
- systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesSkillsJul 2026
- safe-debugRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training SkillsMay 2026
- explore-runRigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subseSkillsMay 2026
- minimal-run-and-auditRigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation SkillsMay 2026
- insforge-debugUse when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denSkillsJul 2026
