cost-opt
Compact cost logs, recalibrate the pricing table in ~/.claude/extract_cost.py and statusline-command.sh against platform.claude.com/cost extracts, and surface…
Skill by laurac8r
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/laurac8r-cost-opt
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/cost-opt
What's inside
- Skill name
cost-opt- Description
- Compact cost logs, recalibrate the pricing table in ~/.claude/extract_cost.py and statusline-command.sh against platform.claude.com/cost extracts, and surface optimization suggestions.
- License
- MIT
- Instructions
- 27 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
1. First, ensure logs exist by running:
`python3 ~/.claude/extract_cost.py --append-log --quiet`
2. Read the JSONL cost log files in `~/.claude/cost-log/*.jsonl` and the
existing `~/.claude/COST-SUMMARY.md`.
3. Recalibrate and update `~/.claude/extract_cost.py` `PRICING` table and the
`~/.claude/statusline-command.sh` `case "$model_id"` pricing block, based on
the `~/.claude/cost-log/*.csv` actual extracts from
- `https://platform.claude.com/cost` (cost-by-day), and
- `https://platform.claude.com/logs` (historical API logs) –> The user will
periodically fetch these extracts themselves and upload them to
`~/.claude/cost-log`.
4. Perform an efficient `/compact` summary on the log files (just changes since
last summary) and update `SUMMARY.md` with the compacted summary including:
total spend, spend by model, spend by project, busiest sessions, and trends.
5. Suggest cost optimizations based on the data — e.g., sessions where Opus was
used for tasks that Sonnet could handle, high cache-creation ratios, or
sessions with excessive turns.
6. **Ignore and filter out** work done on the `~/.claude` and `~/.awesome`
directories, in the cost analysis, summary and recommendations.
7. **Formatting rule — escape dollar signs:** In prose sections (bullet points,
numbered lists, paragraphs), always write `\$` instead of bare `$` to prevent
Markdown renderers from interpreting `$...$` as LaTeX math. Dollar signs
inside tables and fenced code blocks do NOT need escaping. Never break a
dollar amount across lines.From laurac8r/claude-damn, MIT.
More from laurac8r/claude-damn
- 0.564score
check-yourself
laurac8r
Use when a discrete task boundary is crossed in multi-step work — step completion, subagent dispatch return, Skill-tool invocation return, /proceed gate…
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
atlas
laurac8r
Render a single "where am I, what have I done, what's next" survey HTML page composing anchor cascade + tesseract shelf + git state + CHECKPOINT.md + TaskList.
SkillBFreshness: B★ 3Claude Code +9 - 0.514score
checkpoint-save
laurac8r
Use when pausing work that will be resumed later, when switching contexts, or when the user asks to save a checkpoint.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
add-to-roadmap
laurac8r
Use when you want to append a new task to a specific phase or section of the project ROADMAP.md.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
cat
laurac8r
Subagent-driven development as the explicit combination of /subagent-driven-development (sequential, review-gated execution) and /dispatching-parallel-agents…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
checkpoint-resume
laurac8r
Use when resuming paused work, starting a session where a CHECKPOINT.md exists, or when the user says "continue from checkpoint", "resume", or "pick up where…
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
duper
laurac8r
Isolated git worktree workflow (alias for /using-git-worktrees)
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
duper-tdd-cat
laurac8r
TDD workflow using an isolated git worktree with subagent-driven-development
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
continue
laurac8r
retry last operation attempted before the user interrupted the process, or otherwise continue last attempted tool use
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
expert-cat-review
laurac8r
Expert-level review with each phase dispatched as a parallel subagent
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
expert-duper-tdd-cat-review
laurac8r
Expert-level review with subagents, then fix using TDD in an isolated git worktree with subagents
SkillCFreshness: C★ 3Claude Code +9 - 0.503score
expert-final-review
laurac8r
Final pre-merge gate — verify all PR peer feedback is addressed, then run a full /expert-review
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Apr 24, 2026 (6 months ago)
- Last release
- Jul 19, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/laurac8r/claude-damn
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from laurac8r
- 0.564score
check-yourself
laurac8r
Use when a discrete task boundary is crossed in multi-step work — step completion, subagent dispatch return, Skill-tool invocation return, /proceed gate…
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
atlas
laurac8r
Render a single "where am I, what have I done, what's next" survey HTML page composing anchor cascade + tesseract shelf + git state + CHECKPOINT.md + TaskList.
SkillBFreshness: B★ 3Claude Code +9 - 0.514score
add-to-roadmap
laurac8r
Use when you want to append a new task to a specific phase or section of the project ROADMAP.md.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
checkpoint-save
laurac8r
Use when pausing work that will be resumed later, when switching contexts, or when the user asks to save a checkpoint.
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
checkpoint-resume
laurac8r
Use when resuming paused work, starting a session where a CHECKPOINT.md exists, or when the user says "continue from checkpoint", "resume", or "pick up where…
SkillCFreshness: C★ 3Claude Code +9 - 0.514score
cat
laurac8r
Subagent-driven development as the explicit combination of /subagent-driven-development (sequential, review-gated execution) and /dispatching-parallel-agents…
SkillCFreshness: C★ 3Claude Code +9
Cite this page
cost-opt skill. Agent Mart. https://agentmart.dev/skills/laurac8r-cost-opt (last updated 2026-10-24)