Source: Twitter/X via agent-reach (OpenCLI backend), 2026-07-06. 71 unique tweets across 6 queries. Design principle (from @brian_armstrong, ♥6.1k): keep spend flat with better defaults, routing, and caching — not friction and alerts. So this dashboard is a visibility/routing tool, not a nag.
| # | Pain point | Evidence (reach) | Feature that answers it |
|---|---|---|---|
| 1 | Silent context bloat — Claude Code resends the whole session (system prompt + tools + history) every message; you pay it all as input and never see it | "$20 to type 'hey'" = 847k tokens on one msg, 1.4k upvotes; @theo effort tips ♥8.3k | Context-weight meter per session + est. cost-per-message |
| 2 | Silent Opus misrouting — Fable classifiers fall back to Opus 4.8 on routine coding, and Opus is where the money goes | @bridgemindai "$321 session, 75% routed to Opus" ♥3.6k | Per-model spend split (Fable/Opus/Sonnet/Haiku) |
| 3 | The image-OCR cost trick is viral — turn context into PNGs, cut input ~70% (this is pxpipe) | @IntCyberDigest ♥4.8k, @Polymarket ♥2.7k | pxpipe savings hero — live % + tokens saved |
| 4 | Fable → credit billing urgency — "you have Fable for a few days"; $10/M in, $50/M out after | @shadcn /improve ♥6.3k, @PrajwalTomar, @eliana | Fable Jul-7 countdown + credit-cost estimator |
| 5 | Effort level = furnace — xhigh/max burn quota with worse output | @theo ♥8.3k ("only use high; xhigh is token hungry") | Effort-level surface + usage burn-down |
| 6 | Caching is the real lever | @brian_armstrong ♥6.1k | Cache-efficiency (cache-read vs fresh input) |
Rates used for cost estimates (from the tweets / public pricing, $/M tokens):
- Fable 5: in 10, out 50 (credit billing)
- Opus 4.8: in 5, out 25
- Sonnet 5: in 2, out 10 (introductory, through 2026-08-31; standard $3/$15 from 2026-09-01)
- Haiku 4.5: in 1, out 5
- Cache read ≈ 10% of input rate; cache write ≈ 125% of input rate.
Verified against source (2026-07-20)
Checked the rate table against Anthropic's live pricing page (platform.claude.com/docs/en/docs/about-claude/pricing, fetched 2026-07-20). Fable 5 (10/50) and the cache multipliers (0.10×/1.25×) were already correct.
- wrong → right: Opus 4.8 "in 15, out 75" → "in 5, out 25." [Evidence: pricing page lists Claude Opus 4.8 at $5/$25; $15/$75 is the retired Claude Opus 4 / deprecated Opus 4.1 rate, not 4.8.]
- wrong → right: Sonnet 5 "in 3, out 15" → "in 2, out 10 (introductory through 2026-08-31; standard $3/$15 from 2026-09-01)." [Evidence: pricing page: "Introductory pricing of $2/$10 ... in effect through August 31, 2026, after which the standard pricing of $3/$15 ... will take effect." This was already wrong on the 2026-07-06 capture date, not just stale now.]
- wrong → right: Haiku 4.5 "in 0.80, out 4" → "in 1, out 5." [Evidence: pricing page lists Claude Haiku 4.5 at $1/$5; $0.80/$4 is the retired Claude Haiku 3.5 rate.]