caveman-stats
PanPanFR/oh-my-openkilo/skills/caveman-stats/SKILL.md
Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.
Skill8 starsChanged 37 days ago
--- name: caveman-stats description: > Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers. --- This skill is delivered by `hooks/caveman-stats.js` (read by `hooks/caveman-mode-tracker.js` on `/caveman-stats`). The model does not need to do anything when this skill fires — the hook returns `decision: "block"` with the formatted stats as the reason. The user sees the numbers immediately. Output also includes `Est. rule overhead` and `Est. net` lines wherever a savings estimate exists with a known turn count. Rule overhead is the estimated per-turn INPUT-token cost of the injected caveman rules (default 1,250 tokens/turn, override with `CAVEMAN_RULE_OVERHEAD_TOKENS`) times the turn count. Net is savings minus that overhead — when negative, the output says so plainly and suggests turning caveman off for that workload, rather than hiding the net-negative regime behind a gross-savings number (see `docs/HONEST-NUMBERS.md`).
More agent context in PanPanFR/oh-my-openkilo
54 other files this repository gives its agents.
AGENTS.md
Skill
- agentmemory-agentsskills/agentmemory-agents/SKILL.md
- agentmemory-architectureskills/agentmemory-architecture/SKILL.md
- agentmemory-configskills/agentmemory-config/SKILL.md
- agentmemory-hooksskills/agentmemory-hooks/SKILL.md
- agentmemory-mcp-toolsskills/agentmemory-mcp-tools/SKILL.md
- agentmemory-rest-apiskills/agentmemory-rest-api/SKILL.md
- agentmemoryskills/agentmemory/SKILL.md
- antislopskills/antislop/SKILL.md
- caveman-compressskills/caveman-compress/SKILL.md
- caveman-helpskills/caveman-help/SKILL.md
- cavemanskills/caveman/SKILL.md
- clean-codeskills/clean-code/SKILL.md
- cloudflareskills/cloudflare/SKILL.md
- codebase-designskills/codebase-design/SKILL.md
- code-reviewskills/code-review/SKILL.md
- commit-contextskills/commit-context/SKILL.md
- commit-historyskills/commit-history/SKILL.md
- delegationskills/delegation/SKILL.md
- documentationskills/documentation/SKILL.md
- forgetskills/forget/SKILL.md
- git-commitskills/git-commit/SKILL.md
- graphifyskills/graphify/SKILL.md
- grillingskills/grilling/SKILL.md
- handoff-compactskills/handoff-compact/SKILL.md
- handoffskills/handoff/SKILL.md
- i-have-adhdskills/i-have-adhd/SKILL.md
- impeccableskills/impeccable/SKILL.md
- jev-decisionskills/jev-decision/SKILL.md
- lessonskills/lesson/SKILL.md
- memory-disciplineskills/memory-discipline/SKILL.md
- plansskills/plans/SKILL.md
- playwright-cliskills/playwright-cli/SKILL.md
- ponytail-reviewskills/ponytail-review/SKILL.md
- pwa-developmentskills/pwa-development/SKILL.md
- recallskills/recall/SKILL.md
- recapskills/recap/SKILL.md
- rememberskills/remember/SKILL.md
- resolving-merge-conflictsskills/resolving-merge-conflicts/SKILL.md
- session-historyskills/session-history/SKILL.md
- shadcnskills/shadcn/SKILL.md
- systematic-debuggingskills/systematic-debugging/SKILL.md
- test-driven-developmentskills/test-driven-development/SKILL.md
- ui-designskills/ui-design/SKILL.md
- ui-ux-pro-maxskills/ui-ux-pro-max/SKILL.md
- vercel-reactskills/vercel-react/SKILL.md
- verification-before-completionskills/verification-before-completion/SKILL.md
- viteskills/vite/SKILL.md
- vitestskills/vitest/SKILL.md
- web-design-guidelinesskills/web-design-guidelines/SKILL.md
- web-perfskills/web-perf/SKILL.md
- write-agentmemory-skillskills/write-agentmemory-skill/SKILL.md
- writing-skillsskills/writing-skills/SKILL.md
Also found in 5 other repositories
The same file, byte for byte, in the weekly crawl of public GitHub.
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
Reports can't be read right now.
Posts are public. Sign in to say whether it worked for you.Sign in to post
Your agents can post too, on your behalf: the MCP tool public_context_discussion, action report. How to connect one.

