From 75ca893b9e2724659bec257a737370fc9dd913a8 Mon Sep 17 00:00:00 2001 From: Claude Date: Sat, 14 Mar 2026 19:23:26 +0000 Subject: [PATCH 1/2] docs: add Costs section to README with token usage and cost breakdown Adds a new ## Costs section summarizing observed LLM costs based on maintainer testing (~82 requests, 246k tokens). Includes a stats table (avg, 95th percentile, peak), a token breakdown table, and a key insight explaining that output tokens drive ~50% of cost despite being only 17% of volume. Includes a disclaimer that figures are based on personal testing. https://claude.ai/code/session_01Raf7fKQax1GZEFoYUsGyxD --- README.md | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/README.md b/README.md index 7ab9560..0dd0d68 100644 --- a/README.md +++ b/README.md @@ -488,6 +488,33 @@ The PR comment is always posted — with a GIF if recording succeeded, or screen --- +## Costs + +> **Disclaimer:** The figures below are based on the maintainer's own testing and may not reflect your usage patterns. Token consumption varies significantly by diff size, app complexity, and retry count. Use these numbers as a rough reference only — your costs may be higher or lower. + +Each GitGlimpse run makes one or more LLM calls to generate the Playwright interaction script. The table below summarizes observed costs using `claude-sonnet-4-6` with default settings. + +| Metric | Value | +|---|---| +| Average cost per request | ~$0.015 (1.5¢) | +| 95th percentile | ~$0.035 | +| Peak (max observed) | ~$0.047 | +| Requests per USD | ~66 | +| Sample size | ~82 requests / 246k tokens | + +**Token breakdown (per request, approximate):** + +| Token type | Volume | Share of tokens | Share of cost | +|---|---|---|---| +| Input | ~205k total | ~83% | ~50% | +| Output | ~42k total | ~17% | ~50% | + +**Key insight:** Output tokens drive roughly **50% of the cost** despite representing only **17% of the token volume** — a direct consequence of output tokens being priced ~5× higher than input tokens in most Claude pricing tiers. Reducing script verbosity or capping `maxDuration` can lower output token counts and trim costs noticeably. + +For high-frequency teams, use `trigger.mode: 'smart'` or `'on-demand'` to avoid running the LLM on every push. + +--- + ## Development ```bash From 4f7c1b2b0b9081ad2b35dd414a8ae15cfd4378ba Mon Sep 17 00:00:00 2001 From: Claude Date: Sat, 14 Mar 2026 19:31:03 +0000 Subject: [PATCH 2/2] docs: remove key insight from Costs, add Roadmap section Drops the "Key insight" paragraph from ## Costs per feedback. Adds a new ## Roadmap section covering two planned items: - Multiple preview URL / starting point support - GitHub App for lower-friction installation https://claude.ai/code/session_01Raf7fKQax1GZEFoYUsGyxD --- README.md | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 0dd0d68..434e3f0 100644 --- a/README.md +++ b/README.md @@ -509,8 +509,6 @@ Each GitGlimpse run makes one or more LLM calls to generate the Playwright inter | Input | ~205k total | ~83% | ~50% | | Output | ~42k total | ~17% | ~50% | -**Key insight:** Output tokens drive roughly **50% of the cost** despite representing only **17% of the token volume** — a direct consequence of output tokens being priced ~5× higher than input tokens in most Claude pricing tiers. Reducing script verbosity or capping `maxDuration` can lower output token counts and trim costs noticeably. - For high-frequency teams, use `trigger.mode: 'smart'` or `'on-demand'` to avoid running the LLM on every push. --- @@ -529,6 +527,13 @@ See [CLAUDE.md](CLAUDE.md) for repo structure and contributor notes. --- +## Roadmap + +- **Multiple preview URL support** — currently GitGlimpse accepts a single preview URL per run; planned support for specifying multiple starting points so a single PR can record demos across several routes or environments simultaneously. +- **GitHub App** — a first-party GitHub App to reduce setup friction: no workflow files to copy, no secrets to configure manually, and automatic installation across repos in an organization. + +--- + ## License MIT