token-optimizer

# Token Optimizer

Audits a Claude Code or Codex setup, identifies context window waste, implements fixes, and measures savings.

**Target**: 5-15% context recovery through config cleanup, up to 25%+ with autocompact management.

---

## Codex Runtime

If `TOKEN_OPTIMIZER_RUNTIME=codex` or Codex environment is detected, read `references/codex-workflow.md` and follow its chat-first workflow instead of the Claude Code phases below.

---

## OpenCode Runtime

OpenCode loads `~/.claude/skills` by default, so it can invoke this skill even though you are working in OpenCode, not Claude Code. If OpenCode is detected — `TOKEN_OPTIMIZER_RUNTIME=opencode`, any `OPENCODE_*` environment variable, or you are running inside OpenCode — **STOP** and read `references/opencode-workflow.md`. Do **not** run the Claude Code phases below: they scan and modify `~/.claude`, which is the wrong target when the user is in OpenCode (issue #57).

Quick check before Phase 0:
```bash
python3 "$MEASURE_PY" report 2>/dev/null | head -1
# If it prints "Token Optimizer — OpenCode runtime detected.", follow references/opencode-workflow.md and stop.
```

---

## Phase 0: Initialize (Claude Code)

Resolve measure.py path:
```bash
MEASURE_PY=""
for f in "$HOME/.claude/skills/token-optimizer/scripts/measure.py" \
         "$HOME/.claude/plugins/cache"/*/token-optimizer/*/skills/token-optimizer/scripts/measure.py; do
  [ -f "$f" ] && MEASURE_PY="$f" && break
done
[ -z "$MEASURE_PY" ] && { echo "[Error] measure.py not found."; exit 1; }
```

Read `references/phase0-setup.md` for the full setup sequence: context window detection, pre-check, backup, coordination folder, hook checks, daemon setup, and smart compaction.

---

## Phase 0.5: Keep-Warm Consent (first run only, Claude Code)

Keep-Warm is opt-in and pays off only for API-key-billed Claude Code sessions. Ask once:

```bash
python3 "$MEASURE_PY" keepwarm-consent-status   # JSON: {billing_mode, consent, should_ask}
```

If `should_ask` is `false`, skip this phase silently (subscription users are never asked; declined/enabled users keep their choice). If `should_ask` is `true`, first compute the user's own projection, then present the pitch:

```bash
python3 "$MEASURE_PY" keepwarm-backfill --json --no-fence   # read modes."probe-only".net_usd
```

Read `net_usd` under `modes."probe-only"`. If it is a positive number, include it as the projection. If backfill errors, returns nothing, or `net_usd <= 0`, drop the dollar sentence entirely (do not invent a number) and use the no-data wording below.

> **Keep your prompt cache warm automatically?** When a Claude Code session pauses past its 1h cache window and resumes, the whole prefix is re-written at up to 2x input. Keep-Warm pings the cache just before expiry (~0.1x of the prefix, max 2 pings per pause) so a resume stays warm. A history-replay projection from your own last 30 days nets ~$<net_usd>/30d at the conservative probe-only setting. A tripwire auto-disables it if pings ever stop paying for themselves, and you can turn it off any time. Enable it?

No-data wording (when backfill yields no positive projection): drop the projection sentence and say "Your savings depend on your own pause-and-resume pattern; the dashboard will show your number once pings have fired."

Then record the answer (do this exactly once). **Record the yes/no FIRST**, so an interrupted run never strands an "asked" marker with no recorded answer:

```bash
# yes:
python3 "$MEASURE_PY" keepwarm-enable
# no:
python3 "$MEASURE_PY" keepwarm-disable
```

`keepwarm-enable` and `keepwarm-disable` are terminal states, so they already satisfy `should_ask`. Only if the user defers or ignores the question (records neither) run the shown-marker so they are not re-asked next run:

```bash
python3 "$MEASURE_PY" keepwarm-consent-asked          # mark shown (sticky); use ONLY when no enable/disable was recorded
```

`keepwarm-enable` records consent and installs the scheduler (macOS); on other OSes the scheduler is pending, so it is watchdog-only. It refuses on subscription with an honest message. To confirm it is armed:

```bash
python3 "$MEASURE_PY" keepwarm-scheduler status      # JSON: installed/loaded state (macOS)
python3 "$MEASURE_PY" keepwarm-tick --dry-run        # JSON: what the next tick would decide
```

---

## Phase 0.6: Star the repo (first run only, once ever)

A one-time, no-pressure offer to star the repo. It is gated so it only ever surfaces for someone who has already gotten value (the gate checks `gh` is available, the repo is not already starred, and the user has session history). Check the gate:

```bash
python3 "$MEASURE_PY" star-status   # JSON: {consent, gh_available, already_starred, has_value, should_ask}
```

If `should_ask` is `false`, skip this phase silently (already asked, already starred, no `gh`, no value yet, or disabled via `TOKEN_OPTIMIZER_STAR_ASK=0`). If `should_ask` is `true`, make the offer warmly and briefly, and make declining effortless:

> **Enjoying Token Optimizer?** If it's been saving you tokens, a GitHub star helps other people find it. Want me to star it for you? (One tap, and I won't ask again either way.)

Then record the answer exactly once:

```bash
# yes:
python3 "$MEASURE_PY" star-now        # runs gh api -X PUT /user/starred/...; sets consent=starred
# no:
python3 "$MEASURE_PY" star-decline    # terminal; never asked again
```

Only if the user defers or ignores the question (records neither) mark it shown so they are not re-asked:

```bash
python3 "$MEASURE_PY" star-consent-asked   # mark shown (sticky); use ONLY when no star/decline was recorded
```

---

## Phase 1: Quick Audit (Parallel Agents)

Read `references/agent-prompts.md` for all prompt templates.

Dispatch 6 agents in parallel:

| Agent | Output File | Model | Task |
|-------|-------------|-------|------|
| CLAUDE.md Auditor | `audit/claudemd.md` | sonnet | Size, duplication, tiered content, cache structure |
| MEMORY.md Auditor | `audit/memorymd.