pulselisted

# /pulse — Self Snapshot Refresh **Conduct ALL conversation with the user in the language defined by `.claude/rules/personal-language.md`** (or the user's input language if absent). The English instructions below are for skill clarity, not for output style. Exceptions (only): tokens inside backticks or code blocks, proper nouns, ASCII acronyms. > **Tool references in this skill** (`Bash`, `Grep`, `Read`, `Edit`, `Glob`, `Skill`) describe **intent**, not Claude-specific tool calls. Each harness should map them to its native equivalent. Aggregates active state from `workspace/`, `tasks/`, and `knowledge/self/` and writes a triaged snapshot to `knowledge/self/current-state.md`. The snapshot has a **hard cap of 80 lines / 2 screens** with each section limited to 7 entries (5 for known contradictions). Design references: - `workspace/2026-05-07-dream-system-rill-application/009-pulse-skill-detail-design.md` — full spec - `workspace/2026-05-07-dream-system-rill-application/010-pulse-token-cost-analysis.md` — Grep-first 4-stage pipeline (~30-42K tokens / run) - `workspace/2026-05-07-dream-system-rill-application/015-execution-wiring.md` — Auto-chain trigger paths ## Arguments $ARGUMENTS — one of the following: - Omitted → normal run (12h cooldown applies) - `--force` → bypass the 12h cooldown - `--dry-run` → produce the output and print to stdout; do not write `knowledge/self/current-state.md` ## Trigger Model Three trigger kinds (see 009 §1.1): | Trigger | Source | Cooldow