Agent skill

Aider Prompt Caching Default

by OnlyTerp in OnlyTerp/prompt-cache-skills

Patch recipe that turns on Aider's --cache-prompts by default for models that support caching, with a verification procedure against the wire request.

Custom licenceAuto-check passedAI & LLM Engineering

Install Aider Prompt Caching Default

skills CLI
$ npx skills add OnlyTerp/prompt-cache-skills --skill aider-cache-default-on -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install OnlyTerp/prompt-cache-skills aider-cache-default-on --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/OnlyTerp/prompt-cache-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/aider-cache-default-on .claude/skills/aider-cache-default-on && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
aider-cache-default-on
GitHub stars
114
Token cost
~638 tokens
SKILL.md length
227 words
Files
1
Skills in repo
13
Repo updated
First seen
Licence
Custom licence

At a glance

Patch recipe that turns on Aider's --cache-prompts by default for models that support caching, with a verification procedure against the wire request.

  • Works in 4 steps: Run aider --model… → Capture wire. → Request body should contain… → …
  • Contributing a patch that enables prompt caching by default in Aider
  • SKILL.md covers Target, Symptom, Fix and Verify, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The target is aider/args.py in the Aider repository, where the --cache-prompts flag is defined with default=False. Aider already implements the four-breakpoint Anthropic caching pattern correctly, but most users never see the benefit because they must know to enable it by flag, config file or environment variable.

The fix flips the default to True. A per-model cache_control setting in aider/models.py already stops caching from being sent to models that do not support it, so the change only moves caching from opt-in to opt-out. The recipe also asks for a CHANGELOG note.

To verify, run aider with claude-3-7-sonnet-20250219 and no cache flag or config entry, capture the request on the wire, and confirm the body carries an ephemeral cache_control marker at the four breakpoints for system, repo map, files and current message, and that the second turn reports cache_read_input_tokens above zero. The background argues the 1.25x cache-write premium is small and repaid after the second hit, and notes that Cline, Roo and OpenCode already default to caching.

When your agent uses it

  • Contributing a patch that enables prompt caching by default in Aider
  • Checking whether Aider requests actually carry cache_control markers

Example prompts

  • “Make --cache-prompts default to on in Aider's args.py and add the CHANGELOG note.”
  • “Verify that a plain Aider run with a Claude model sends cache_control on all four breakpoints.”

Requirements

  • A checkout of the Aider repository
  • An Anthropic model and API access for the wire check

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Run aider --model claude-3-7-sonnet-20250219 with NO mention of
  2. Capture wire.
  3. Request body should contain cache_control: {"type": "ephemeral"}
  4. Confirm 2nd-turn usage.cache_read_input_tokens > 0.

What it can do on your machine

Read from SKILL.md and the folder at commit 5b58ae2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are diff).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Aider Prompt Caching Default loads about 638 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 227 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~638

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 227 words (~638 tokens).

“aider/args.py in Aider-AI/aider. The --cache-prompts flag is defined here with default=False.”

— opening of SKILL.md by OnlyTerp, Custom licence
name
aider-cache-default-on
target_harness
Aider
target_repo
Aider-AI/aider
target_files
aider/args.py
target_commit
3ec8ec5a
estimated_savings
90% input discount for every user who didn't know to set the flag

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/aider-cache-default-on of OnlyTerp/prompt-cache-skills.

Open the folder on GitHubat commit 5b58ae2

Compare with similar skills

Aider Prompt Caching Default next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Aider Prompt Caching Default compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Aider Prompt Caching Default this skillOnlyTerp/prompt-cache-skills114—~638Automated safety check: PassCustom licence
Dt Obs GenaiDynatrace/dynatrace-for-ai161—~4.5kAutomated safety check: PassApache-2.0
Prefix Cache Replaybenchflow-ai/skillsbench1.8k—~2.3kAutomated safety check: PassApache-2.0
Cache Credits AnalyzerTsinHzl/kiro2cc-proxy164—~1.1kAutomated safety check: PassMIT
Prompt Cachingdavila7/claude-code-templates32k6 repos~452Automated safety check: PassMIT
LLM Cost Optimizationsickn33/agentic-awesome-skills47k1 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • Dt Obs Genai

    Dynatrace/dynatrace-for-ai

    Analyze & debug GenAI/LLM apps: token cost & caching by prompt, model & provider; latency/errors; agent & tool loops/failures; conversations; guardrails; evaluations; OpenTelemetry/dt-evals setup.

    161 GitHub stars~4.5k tokensUpdated 6 days ago
    AI & LLM EngineeringAuto-check passed
  • Prefix Cache Replay

    benchflow-ai/skillsbench

    Replay an LLM inference request trace (Mooncake / vLLM / SGLang hashids format) against a block-level KV prefix cache and compute hit statistics.

    1.8k GitHub stars~2.3k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check passed
  • Cache Credits Analyzer

    TsinHzl/kiro2cc-proxy

    分析 kiro2cc-proxy 访问日志,计算 Prompt Caching 节省的 credits。只要用户粘贴了含有"输入token 输出token 费用$ credits✓"格式的日志行,并询问节省了多少credits、缓存效率、cost分析等,立即使用此 skill。触发关键词:节省了多少credits、cache节省、分析日志、caching…

    164 GitHub stars~1.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Prompt Caching

    davila7/claude-code-templates

    Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache…

    32k GitHub starsUsed in 6 repos~452 tokens
    Backend & APIsAuto-check passed
  • LLM Cost Optimization

    sickn33/agentic-awesome-skills

    Reduce LLM API and infrastructure costs through model selection, prompt caching, batching, caching, quantization, and self-hosting strategies.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    AI & LLM EngineeringAuto-check passed
  • LLM Gateway

    sickn33/agentic-awesome-skills

    Deploy an API gateway for LLM traffic with load balancing, rate limiting, key management, semantic caching, fallback routing, and cost tracking.

    47k GitHub starsUsed in 1 repo~2.1k tokens
    Backend & APIsAuto-check passed

More from OnlyTerp/prompt-cache-skills

All 13 skills in this repo
  • Aider One-Hour Cache TTL

    OnlyTerp/prompt-cache-skills

    Patches Aider to request Anthropic's one-hour prompt cache lifetime, so long pauses between turns no longer expire the cache or need paid keepalive pings.

    114 GitHub stars~990 tokensUpdated 1 mo ago
    Auto-check passed
  • Cline Prompt Cache Ladder Check

    OnlyTerp/prompt-cache-skills

    Verifies how Cline marks Anthropic prompt-cache breakpoints on the wire, then adds a tools breakpoint and tunes the cache TTL in its AI SDK code.

    114 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed
  • Cline OpenAI Prompt Cache Key Fix

    OnlyTerp/prompt-cache-skills

    Patch guide for adding a stable per-task prompt_cache_key to Cline's OpenAI native provider so cached token counts stop reading as zero.

    114 GitHub stars~868 tokensUpdated 1 mo ago
    Auto-check passed
  • Cline Pin Timestamp

    OnlyTerp/prompt-cache-skills

    Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.

    114 GitHub stars~751 tokensUpdated 1 mo ago
    Auto-check passed
  • Continue Enable Defaults

    OnlyTerp/prompt-cache-skills

    Continue's prompt caching is opt-in via config and off by default.

    114 GitHub stars~977 tokensUpdated 1 mo ago
    Auto-check passed
  • Continue Gemini Explicit

    OnlyTerp/prompt-cache-skills

    Continue's Gemini provider doesn't use the cachedContents API at all.

    114 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Aider Prompt Caching Default

What does Aider Prompt Caching Default do?

Patch recipe that turns on Aider's --cache-prompts by default for models that support caching, with a verification procedure against the wire request. py in the Aider repository, where the --cache-prompts flag is defined with default=False. Aider already implements the four-breakpoint Anthropic caching pattern correctly, but most users never see the benefit because they must know to enable it by flag, config file or environment variable.

When should I use Aider Prompt Caching Default?

Aider Prompt Caching Default fits situations like: contributing a patch that enables prompt caching by default in Aider; checking whether Aider requests actually carry cache_control markers.

How do I install Aider Prompt Caching Default in Claude Code?

Run `npx skills add OnlyTerp/prompt-cache-skills --skill aider-cache-default-on -a claude-code`. Or copy the skill folder (skills/aider-cache-default-on in OnlyTerp/prompt-cache-skills) into .claude/skills/aider-cache-default-on in your project. Claude Code loads it when a task matches its description.

How do I install Aider Prompt Caching Default in Codex?

Run `npx skills add OnlyTerp/prompt-cache-skills --skill aider-cache-default-on -a codex`. Or copy the skill folder (skills/aider-cache-default-on in OnlyTerp/prompt-cache-skills) into .agents/skills/aider-cache-default-on in your project. Codex loads it when a task matches its description.

Can I use Aider Prompt Caching Default in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OnlyTerp/prompt-cache-skills --skill aider-cache-default-on -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/aider-cache-default-on, .gemini/skills/aider-cache-default-on, .github/skills/aider-cache-default-on and .opencode/skills/aider-cache-default-on in your project.

What does Aider Prompt Caching Default need to run?

SKILL.md names no scripts, command-line tools or credentials: Aider Prompt Caching Default is instructions for the agent only. Our summary lists: A checkout of the Aider repository; An Anthropic model and API access for the wire check.

Does Aider Prompt Caching Default access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Aider Prompt Caching Default safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Aider Prompt Caching Default use?

Aider Prompt Caching Default has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Aider Prompt Caching Default use?

About 638 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Aider Prompt Caching Default?

Skills that share tags, products or a category with Aider Prompt Caching Default: Dt Obs Genai (Dynatrace/dynatrace-for-ai, 161 stars), Prefix Cache Replay (benchflow-ai/skillsbench, 1.8k stars), Cache Credits Analyzer (TsinHzl/kiro2cc-proxy, 164 stars) and Prompt Caching (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Aider Prompt Caching Default?

OnlyTerp (a GitHub user) maintains it in OnlyTerp/prompt-cache-skills, which has 114 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on August 29, 2026.

Source: OnlyTerp/prompt-cache-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.