Repository navigation
Conversation
release: v1.2.0 — audit wave 1 (Tier 1 rewrite)
…2-8) Replace invented model speed/quality/cost tables and the "$1,200 to $380" anecdote with the four real speed levers: /fast (Opus-only research preview), /effort, real parallelism (subagents, -w worktrees, Ctrl+B backgrounding), and context size. DEMO uses real claude -p timings and a real `git worktree list` capture instead of invented numbers. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
…W2-8) Replace "think step by step" and the CLAUDE.md-examples narrative with a deterministic quality gate: a PostToolUse lint hook, a Stop test hook, and a fresh-context .claude/agents/reviewer.md, backed by S1/S3/S7/S11/S12. DEMO commands were run for real in ~/cc-lab (eslint --fix, npm test, /output-style); the reviewer-subagent transcript is marked AUTHOR-CAPTURE because a plugin in this environment intercepted the subagent's final message. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
…udit W2-8) Replace 2024-era prices ($15/$75 Opus, $0.25/$1.25 Haiku), the "5x Sonnet" line, and the invented "$1,200 to $380" case with the current pricing table (checked against platform.claude.com/docs 2026-09-27), automatic prompt caching mechanics, a real --max-budget-usd stop, and the S15 cost ladder. No 1M-context surcharge (Delta5). Adds the costs-page $13/day quote to the S15 registry row. DEMO numbers (cache hit/miss cost, budget-cap stop) come from real claude -p runs in ~/cc-lab. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
thucle99
force-pushed
the
feat/audit-w2-optimization
branch
from
October 1, 2026 23:08
f5ca08a to
3b34d06
Compare
This branch was successfully deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Modules 14.2 Speed, 14.3 Quality, 14.4 Cost rewritten for Claude Code v2.1.283 (EN + VI, 6 files).
/fast/effortcaching, X1/X2/X16 ("$1,200→$380", model-score tables removed), §9.3 verify (S1, S7), writer≠reviewer (S3, S12), cost ladder (S15), token multipliers (S10, S15), evals (S11).--max-budget-usdstop). No prompt run in fast mode.🤖 Generated with Claude Code