Menü
Append a structured entry to the agent log with automatic rotation
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | log |
| description | Append a structured entry to the agent log with automatic rotation |
| user_invocable | false |
| args | run_id=<id> skill=<name> status=<SUCCESS|FAILED|WARNING> detail=<message> |
Append a structured log entry to <workspace>/.claude/memory/agent-log.md. This skill owns the log format, creation, and rotation. All other skills and agents call this instead of writing to the log directly.
Setup — Resolve <workspace>: The skill's base directory is <workspace>/.claude/skills/log/; walk up three directory levels and validate that <workspace>/.claude/.workspace exists. Use this <workspace> for all path references below. Abort with a setup-broken error if validation fails.
Parse input: Extract the fields from the arguments:
run_id — Identifier linking related entries (e.g., cos-2026-04-11-1). Use manual if no run ID was provided.skill — Name of the skill or agent that produced this entrystatus — SUCCESS, WARNING, or FAILEDdetail — Brief description (item counts on success, error reason on failure)Check if log file exists: Read <workspace>/.claude/memory/agent-log.md.
# Agent Log
| Timestamp | Run ID | Skill | Status | Detail |
|-----------|--------|-------|--------|--------|
Append the entry: Add a new row with the current timestamp in ISO 8601 format (e.g., 2026-04-11T17:30Z).
Rotate: Count the data rows (excluding the header and separator lines). If there are more than 200, remove the oldest rows to keep exactly 200. Historical entries are preserved in git history.
No output: This skill is silent — it does not print anything to the user. It is a utility called by other skills.
Authoritative, version-pinned reference for every Claude Code CLI flag, classified by whether it works in an INTERACTIVE session (default TUI), a HEADLESS session (-p/--print), or BOTH — plus the canonical launch recipes for each mode. Use when any session needs to launch or script `claude` and must know which switch is valid in which mode, build a headless/streaming invocation, set up remote-control or an always-on session, pass model/effort/permissions/MCP/plugin/settings flags, or answer "does flag X work with -p / in interactive". Trigger: "claude flags", "claude cli switches", "which flags work headless vs interactive", "-p flags", "stream-json flags", "how do I launch claude with X", "/claude-cli-flags".
Authoritative, version-pinned reference for every built-in Claude Code slash (/) command — what each does, its aliases, and which are bundled Skills/Workflows vs fixed built-ins — plus how custom slash commands work (the commands-merged-into-skills model, file locations, frontmatter, arguments, !bash, @file). Includes the full /loop vs /schedule breakdown. Use when any session needs to know what a slash command does, find the right command for a task (clear context, switch model, review code, schedule work, background a task), or author a custom /command. Trigger: "claude slash commands", "what does /X do", "list the slash commands", "built-in commands", "custom slash command", "/loop vs /schedule", "how do I make a /command", "/claude-slash-commands". Sibling of claude-cli-flags (launch flags).
Initialise a workspace, register projects under it, or sync upstream changes. Single entry point for workspace lifecycle.
Enforce coordinated integration testing — identify tool dependencies, check running systems, test all 4 levels (unit/component/integration/system), never disrupt workflows
Autonomous task loop — runs a task repeatedly until completion criteria are met. No babysitting required.
Dual-model review — runs the same question past a second, independent reasoner (a separate model/CLI, e.g. Codex) and synthesizes the disagreements with the primary Claude take. Use before an irreversible call — architecture, security, strategy, high-blast-radius code. Trigger phrases "second opinion", "/second-opinion", "review this", "get another perspective", "sanity check this plan".