telemetrylisted

Analyze **this project** (read name from CLAUDE.md) agent execution telemetry — token usage, API cost estimates, run throughput, and performance trends across all `sr-*` agents. **Input:** `$ARGUMENTS` — optional flags: - `--period <filter>` — time window for analysis. Values: `today`, `week`, `all`. Default: `week`. - `--agent <name>` — focus on a single agent (e.g. `sr-developer`). Default: all agents. - `--format <fmt>` — output format: `markdown` or `json`. Default: `markdown`. - `--save` — write a snapshot to `.claude/telemetry/` after display. --- ## Phase 0: Argument Parsing Parse `$ARGUMENTS` to set runtime variables. **Variables to set:** - `PERIOD` — `"today"`, `"week"`, or `"all"`. Default: `"week"`. - `AGENT_FILTER` — string or empty string. Default: `""` (all agents). - `FORMAT` — `"markdown"` or `"json"`. Default: `"markdown"`. - `SAVE_SNAPSHOT` — boolean. Default: `false`. - `PERIOD_START` — ISO datetime lower bound derived from `PERIOD` and the current date/time. Set to `null` for `"all"`. **Parsing rules:** 1. Scan `$ARGUMENTS` for `--period <value>`. Valid values: `today`, `week`, `all`. If an unknown value is found: print `Error: unknown period "<value>". Valid: today, week, all` and stop. Strip from arguments. 2. Scan for `--agent <name>`. If found, set `AGENT_FILTER=<name>` (lowercase, strip leading `sr-` if the user omitted it — always normalize to `sr-<name>` form internally). Strip from arguments. 3. Scan for `--format <value>`. Valid: `markdo