d1c8a76180
agent-workflows: workspace-context-organization autonomous-ai-agents: hermes-agent computer-use devops: hermes-config-bulk-update, hermes-profile-management, holographic-memory, telegram-integration, webhook-subscriptions email: himalaya mcp: native-mcp, searxng-smart-search media: voice-systems, youtube-content mlops: local-vector-memory, qdrant-collection-management productivity: maps, notion, ocr-and-documents project-knowledge-base research: arxiv, blogwatcher, ecosystem-surveillance save-agents-md social-media: social-media-scraping, xurl software-development: agent-self-audit, simplify-code, spike, subagent-driven-development, systematic-debugging, test-driven-development, writing-plans user-response-style
3.1 KiB
name, description, version, author, platforms
| name | description | version | author | platforms | |
|---|---|---|---|---|---|
| agent-self-audit | Pre-execution self-audit for any tool backed by a loaded skill. Prevents the | 1.0.0 | Hermes Agent |
|
agent-self-audit — Pre-Execution Audit for Skill-Loaded Tools
Failure Mode
Skill rules are exceptions to my defaults. I load skills, understand them intellectually, then proceed with default behaviors without self-auditing for the exceptions. The skill's rules are active constraints I must enforce on myself at the moment of action — not reference material I read once and forget. This skill is the fix: re-read the relevant skill section as a literal checklist before composing any action that uses a skill-loaded tool.
The 5-Step Habit
- Load the relevant skill. Use
skill_view(name)to get the full SKILL.md content. - Re-read the rules that conflict with my defaults. Identify the specific constraints that are exceptions to my normal behavior. Do NOT skip this step — intellectual understanding from step 1 is not the same as active constraint enforcement.
- Compose the action. Write the prompt, command, or tool call.
- Audit the action against those rules. Run the Pre-Execution Audit Checklist below. Verify every rule is satisfied.
- Only then execute. If any rule is violated, fix the action and re-audit.
Pre-Execution Audit Checklist
Before executing any action backed by a loaded skill, answer these three questions:
-
Am I following the skill's procedural rules? E.g., using
--resumefor follow-up asks, pointing at file paths instead of pasting content, including required mandate lines. If the skill says "HARD RULE" or "MUST," I must verify compliance explicitly. -
Am I pasting content the target could read from a path? If the target has filesystem access (peer agent, subagent, delegate), point at the absolute path instead of pasting. Only paste inline when content is under ~5 lines or the target genuinely can't access the path.
-
Am I including all required verification handles? E.g., web search mandate lines, "return absolute path / exit code for any side-effect," source URL citations. If the skill requires a specific output format or verification step, include it.
When to Apply
Any time I use a tool backed by a loaded skill: ask-hermes, delegate_task, write_file, patch, cronjob, browser, execute_code, or any other tool where a skill defines rules that are exceptions to my default behavior.
Pitfalls
- I will be tempted to skip step 2 because I just loaded the skill and think I remember. The whole point is that intellectual understanding != active constraint. Always re-read.
- I will be tempted to audit from memory instead of re-reading the skill text. Memory is lossy — the skill text is canonical. Re-read it.
- I will be tempted to skip the audit entirely for "simple" actions. The simplest actions are where defaults are strongest and exceptions are most likely to be missed.