| name | syncing-agent-output-preferences |
| description | Use when a user rejects an agent output format, system prompt rule, memory habit, or host-agent instruction and wants Hermes, Codex, Claude Code, and OpenClaw behavior made consistent. |
| version | 1.0.0 |
Syncing Agent Output Preferences
Overview
When the user rejects an output contract, fix the durable instruction surfaces, not just the current reply. Check Hermes memory plus host-agent docs for Codex, Claude Code, and OpenClaw.
When to Use
Use when the user says:
- "不要这种格式", "别再用 []", "修系统提示词和记忆"
- Codex/Claude/OpenClaw/Hermes output differs
- a style preference should persist across agent hosts
Do not use for one-off formatting requests unless the user asks to remember or unify it.
Workflow
- Load
autonomous-ai-agents/hermes-agent before Hermes config/prompt work.
- If routing/skills are involved, load
software-development/skill-routing-gov.
- Find active prompt surfaces first:
- Hermes repo/current project: nearest
AGENTS.md / CLAUDE.md
- Codex:
~/.codex/AGENTS.md
- Claude Code:
~/.claude/CLAUDE.md
- OpenClaw:
~/.openclaw/workspace/AGENTS.md
- Search only targeted config/workspace roots first. Avoid broad home-directory scans unless needed.
- Remove or rewrite the offending rule in every active surface where it exists.
- Save a compact user memory only if the preference is durable.
- Verify by re-reading the edited section and searching the active host roots for the rejected phrase.
- Report which hosts were changed or already clean.
Known Host Files
- Hermes current project:
AGENTS.md in the active repo or project.
- Codex global:
~/.codex/AGENTS.md.
- Claude Code global:
~/.claude/CLAUDE.md.
- OpenClaw workspace:
~/.openclaw/workspace/AGENTS.md.
References
references/bracketed-audit-output-cleanup.md records the concrete cleanup pattern for rejected bracketed audit fields across Hermes, Codex, Claude Code, and OpenClaw.
Verification Commands
rg -n "Mandatory Output Protocol|TARGET PARAMETER/ASSET|CURRENT CONTEXT|ACTIONABLE TELEMETRY" \
~/.codex ~/.claude ~/.openclaw/workspace ~/.hermes/hermes-agent -g '*.md'
Expected result after removing the bracketed audit format: no matches in active host prompt files.
Pitfalls
- Do not treat Hermes memory as the only source; host agents read their own prompt docs.
- Do not claim Codex/Claude/OpenClaw are fixed without checking their actual files.
- Do not scan all of
~/Library for prompt text; macOS protected paths create noise and timeouts.
- Do not add a new rigid output schema while removing another one.
