cost-reflect

# Cost Reflect Runs a structural cost audit over the last 7 days of `cost-log.jsonl` and delivers the result to the operator. The math is done by a script — your job is to run it and deliver the output through the right channel. ## Step 0 — Channel reply If this skill was invoked from a channel-arrived message (the inbound prompt contains a `<channel source="...">` tag), reply via that channel's reply tool. Otherwise emit to conversation. ## Step 1 — Run the analyzer On a channel-tagged turn (Step 0 detected a `<channel source="...">` tag), run the plain-language mode instead of the full breakdown — a channel operator asking "why is my bill high" shouldn't get raw token-category jargon: ``` bun ${CLAUDE_PLUGIN_ROOT}/scripts/cost-reflect.ts .claude-code-hermit --plain ``` Otherwise (terminal/dev use), run the full breakdown: ``` bun ${CLAUDE_PLUGIN_ROOT}/scripts/cost-reflect.ts .claude-code-hermit ``` Capture stdout. If the output starts with "No cost data" or "No spend recorded yet", report that message and stop — there's nothing to send. ## Step 2 — Relay the report **Terminal:** the script output is already formatted and capped at 1500 characters. Relay it verbatim. Don't summarize, reformat, or add commentary — the output is the report. **Channel (`--plain` output):** the script output is already plain language and jargon-free — no `cache_read`/`cache_write`/token-type labels, no session IDs, no `PROP-`/`S-NNN`, no slash commands. Relay it **translated into the...