一键在 Manus 中运行任何 Skill

caveman-stats

星标4

分支0

更新时间2026年5月15日 02:23

Use when the user invokes /caveman-stats or asks for caveman token-usage stats. Shows real token usage and estimated savings for the current session, read directly from the Claude Code session log — no AI estimation. Output is injected by the `caveman-mode-tracker` hook (vendored alongside this skill), which intercepts the slash command and returns the formatted stats as a blocked-decision reason.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

danmestas

danmestas/wardrobe

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

Caveman Stats

This skill is delivered by the hooks/caveman-mode-tracker hook, which intercepts /caveman-stats on UserPromptSubmit and runs the bundled caveman-stats.js against the active Claude Code session transcript. The hook returns decision: "block" with the formatted stats as the reason — the user sees real token counts and estimated savings immediately, and the model never has to compute or estimate anything.

Numbers come from the JSONL session log on disk:

output_tokens and cache_read_input_tokens summed across every assistant turn.
Estimated savings derived from the mean per-task ratio recorded in caveman-stats.js (COMPRESSION table — currently only full mode has benchmark data; other modes report no estimate).
Lifetime aggregation across sessions via /caveman-stats --all or /caveman-stats --since 7d, backed by ~/.claude/.caveman-history.jsonl.

If the hook isn't registered in the active settings, the slash command falls through to the model — surface that fact and point the user at the wardrobe hooks/caveman-mode-tracker component (or the upstream installer at https://github.com/JuliusBrussee/caveman).

同仓库更多 Skills

同仓库

helland

danmestas/wardrobe

The Pat Helland lens: treat durable data as immutable, append-only facts that carry their own identity and version; and design across service, machine, or org boundaries assuming you cannot have distributed transactions — only idempotent, at-least-once messages that must be reconciled. Apply this on in-place updates and overwrites, "just UPDATE the row," two-phase commit or distributed transactions at scale, exactly-once delivery assumptions, shared mutable state across services, and any data that crosses a boundary of service, machine, org, or time. Trigger even when Helland isn't named — the smell is mutation-in-place and pretending distributed systems can be transactional.

2026-07-184

hickey

danmestas/wardrobe

The Rich Hickey lens: pursue simple (un-braided, one role) over easy (familiar, near-at-hand), decomplect concerns that got tangled together, and separate value, identity, state, and time. Apply this whenever "easy," "convenient," or "it's what we already use" is doing the work of justifying a design; when state is braided into logic, policy into mechanism, or data into behavior; when object-soup would be plainer as data; and when a hard design decision is being made at the keyboard under time pressure instead of thought through first. Trigger even when Hickey isn't named — the smell is complecting, and confusing "easy" with "simple."

2026-07-184

carmack

danmestas/wardrobe

The John Carmack lens: minimize the mutable state you have to reason about, do the simple thing before the clever one, and treat correctness tooling — static analysis, warnings-as-errors, determinism — as non-negotiable. Apply this on sprawling mutable state, "we'll clean it up later," debugging by print- statement whack-a-mole, silenced compiler warnings, nondeterministic or non-reproducible behavior, premature abstraction, perf work that skips measurement, and any "what should we actually work on" prioritization call. Trigger even when Carmack isn't named — the smell is code whose full set of states you can't hold in your head, and effort that isn't ruthlessly focused.

2026-07-184

bellard

danmestas/wardrobe

The Fabrice Bellard lens: build the smallest self-contained thing that fully does the job, get performance from insight instead of hardware, and reuse existing machinery instead of reinventing it. Apply this whenever code is growing dependencies, frameworks, services, or infrastructure to solve a problem that a smaller, sharper implementation could handle — or whenever someone says a thing needs a cluster, a big framework, or a rewrite. Use for size/complexity audits, "do we really need this dependency/service?" questions, performance work where the reflex is to add hardware or caching, green-field "should this be one file or a platform?" decisions, and any moment the answer is trending toward "that's impractical, you'd need X." Trigger even when the user doesn't name Bellard — the smell is scope inflation and reaching for resources over insight.

2026-07-184

vault-autoresearch

danmestas/wardrobe

Use when iteratively researching a topic and filing the synthesis into an Obsidian vault for later ingestion. Output goes to `<vault>/raw/` (NOT directly into wiki pages) so that `vault-ingest` can process it on its own schedule. Triggers: '/vault-autoresearch', 'autoresearch [topic]', 'research [topic] into the vault', 'deep dive into [topic]', 'find everything about [topic] for the vault', 'research and stage'.

2026-07-144

vault-ingest

danmestas/wardrobe

Ingest sources into the Obsidian wiki vault. Reads a source, extracts entities and concepts, creates or updates wiki pages, cross-references, and logs the operation. Supports files, URLs, and batch mode. Triggers on: ingest, process this source, add this to the wiki, read and file this, batch ingest, ingest all of these, ingest this url.

2026-07-144

name	caveman-stats
version	1.0.0
targets	["claude-code"]
type	skill
description	Use when the user invokes /caveman-stats or asks for caveman token-usage stats. Shows real token usage and estimated savings for the current session, read directly from the Claude Code session log — no AI estimation. Output is injected by the `caveman-mode-tracker` hook (vendored alongside this skill), which intercepts the slash command and returns the formatted stats as a blocked-decision reason.
category	{"primary":"economy"}
license	{"upstream":"MIT","source":"https://github.com/JuliusBrussee/caveman@63a91ec","path":"skills/caveman-stats/SKILL.md"}

Caveman Stats

Numbers come from the JSONL session log on disk:

output_tokens and cache_read_input_tokens summed across every assistant turn.
Estimated savings derived from the mean per-task ratio recorded in caveman-stats.js (COMPRESSION table — currently only full mode has benchmark data; other modes report no estimate).
Lifetime aggregation across sessions via /caveman-stats --all or /caveman-stats --since 7d, backed by ~/.claude/.caveman-history.jsonl.