Driving Token Efficiency For AI Agents

$ tj optimize Analyzing 247 sessions, 9.8K spans, 4.0M tokens (last 30d)…   ① Model downgrade: 47% of sessions look Haiku-eligible     • 116 of 247 sessions match structural heuristics     • Currently: claude-opus-4-7, claude-sonnet-4-7     • Suggested target: claude-haiku-4-5     • At current usage: $1,886 → $254 (-86% on flagged sessions)     • Estimated monthly savings: $1,632 (-38% total)      ⚠ Structural heuristic only. Run `tj optimize --validate`       to replay-test on your actual sessions before applying.

Prompt bloat detected in claude-code-myproj:  • Your CLAUDE.md is 4,213 tokens (up 38% in 30 days)  • Section "Coding conventions > Error handling" appears identically    in 91 of 247 sessions (1,108 tokens × 91 = ~100K repeated tokens)  • Significance analysis suggests ~340 of those 1,108 tokens carry    the signal; the rest could be trimmed  • Estimated cost: ~$8.50/mo at current usage on Sonnet   Detail: open `tj report --bloat claude-code-myproj` to see the  highlighted prompt with high-significance tokens bold,  low-significance dimmed.

Cache opportunities in last 30d:  • Identical 2,400-token prefix detected across 94% of your calls    (your CLAUDE.md + tools + system prompt)  → You're already using prompt caching for 11% of cacheable opportunities.  → Increasing cache_control breakpoints could save ~$42/mo (90% reduction     on the 89% of calls currently paying full price).  → See `tj report --cache claude-code-myproj` for the specific config.   • Semantic similarity ≥0.95 detected on 47 instances of "format SQL query"    style requests in last 30d.  → Estimated savings: $8/mo at TTL ≥ 1 day.

Deterministic workflow candidates (high confidence only):  • 23 sessions in last 30d executed identical 5-step sequence:    git pull → npm install → cat .env.staging → npm run build → pm2 restart     Zero argument variation. Zero observed branching.    Estimated current cost: ~$87/mo (23 sessions × ~$3.80 average)   → This looks like a deployment script, not an agent task.    Suggested: replace with `scripts/deploy-staging.sh`.    Estimated savings: $87/mo, plus ~30s latency per execution.

Repeated planning detected (last 30d):  • Cluster "patch-release": 31 sessions share one plan skeleton    (read changelog → bump version → run tests → tag → push)  • Planning portion: ~2,100 tokens/session on claude-opus-4-7  • The skeleton is identical across all 31 runs; only the version    string and date change.  • You paid to generate this plan 31 times.  • Estimated recoverable: ~$54/mo if served from a plan cache    (or ~$61/mo if converted to a slash command)      ⚠ Structural analysis only. Review the exported templates       in `tj report --reuse` before reusing them.