dev-guide-cache-hit-rate

dev-guide-cache-hit-rate is a skill for Claude Code, Codex from Lingtai-AI/lingtai. It costs 152 tokens per session (2,795 once invoked), scanned C, original, Apache-2.0.

Instructions for measuring how often LingTai reuses cached parts of recent requests to its language model. The measurement reads token ledger logs and compares cached input tokens with total input tokens over rolling time windows.

In plain words
What is it for?
Use it to calculate recent cache-use rates from LingTai token logs, compare different time windows, and verify the effect of caching or connection-affinity changes.
Why use it?
It provides an evidence-based way to check whether prompt caching is working instead of guessing from system behavior. It also pairs with runtime checks that confirm whether a related code change was actually rebuilt.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit Use it to calculate recent cache-use rates from LingTai token logs, compare different time windows, and verify the effect of caching or connection-affinity changes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lingtai-ai/lingtai/cache-hit-rate
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Lingtai-AI/lingtai --skill cache-hit-rate
Clone the repo
git clone --depth 1 https://github.com/Lingtai-AI/lingtai

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for dev-guide-cache-hit-rate

README.md
[![agentmods](https://agentmods.dev/badge/skills/lingtai-ai/lingtai/cache-hit-rate/github.svg)](https://agentmods.dev/skills/lingtai-ai/lingtai/cache-hit-rate)
Your own site
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/cache-hit-rate"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/cache-hit-rate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dev-guide-cache-hit-rate

Your own site · 80×15
<a href="https://agentmods.dev/skills/lingtai-ai/lingtai/cache-hit-rate"><img src="https://agentmods.dev/badge/skills/lingtai-ai/lingtai/cache-hit-rate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,795 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 88
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00152 $0.02795
Opus 5 $0.00076 $0.01398
Sonnet 5 $0.00030 $0.00559
Haiku 4.5 $0.00015 $0.00280

Measured 11d ago against content hash e0a2978216da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

dev-guide-cache-hit-rate scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/cache_hit_rate.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$T"
tui/internal/preset/skills/lingtai-dev-guide/reference/cache-hit-rate/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cache Hit Rate

Nested lingtai-dev-guide reference. Read this after the top-level router sends you here when you need to know how well prompt caching has been working recently for one or more LingTai agents, grounded in the token ledger rather than guessed.

This pairs with reference/runtime-self-check/SKILL.md §6: when a cache/affinity fix "should be live," the token ledger is the observable that proves it. This reference is the measurement; runtime-self-check is the did-the-object-rebuild diagnosis.

Core principle

A read-only metric. It only reads append-only logs/token_ledger.jsonl files; it never writes, rotates, or mutates runtime state. Report rates without pasting private absolute paths into human-facing deliverables — the ledger holds no secrets, but its parent paths can be private, so generalize to ~/.lingtai-tui/... or <project>/.lingtai/<agent>/.

Data source: the token ledger

Single source of truth: logs/token_ledger.jsonl, one JSON object per LLM call, written after every call by lingtai/kernel/token_ledger.py (append_token_entry). Required fields:

Field Meaning
ts Call time, UTC, %Y-%m-%dT%H:%M:%SZ (always Z/UTC).
input Total prompt/input tokens for the call. Already includes the cached portion. For the Anthropic/Claude adapters this is raw_input + cache_read + cache_write.
output Output tokens.
thinking Reasoning/thinking tokens.
cached Cache-read input tokens served from the provider prompt cache. A subset of input.
model, endpoint Attribution (which model / base_url produced the tokens).

Optional tags on some entries: source (main, soul, tc_wake, daemon), and for daemon-attributed rows em_id / run_id / api_call_id / codex_*.

The kernel normalizes every provider's usage into these same fields before writing, so the metric is provider-agnostic (verified across gpt-5.5, mimo-v2.5-pro, deepseek-v4-pro, and the Anthropic adapters). Key invariant, confirmed in the adapters (lingtai/llm/anthropic/adapter.py, lingtai/llm/claude_code/adapter.py) and empirically over a full ledger: 0 <= cached <= input, so the hit rate is always in [0, 1].

Read the full file on GitHub · 224 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 224 lines · 152 tokens per session scan C e0a2978216da

Subscribe to this mod's changes

dev-guide-cache-hit-rate is a skill published in the GitHub repository Lingtai-AI/lingtai (670 stars, last pushed yesterday), licensed Apache-2.0. It adds 152 tokens to every session and 2,795 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens