cf-ask

cf-ask is a skill for Claude Code, Codex from dinhanhthi/coding-friend. It costs 68 tokens per session (2,927 once invoked), scanned A, original, MIT.

A codebase question-and-answer skill that searches project files and stored documentation, then saves the answer to project memory.

In plain words
What is it for?
It helps answer focused questions about modules, definitions, data flows, and project decisions.
Why use it?
It reduces the time spent looking through files to understand how a codebase works.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/dinhanhthi/coding-friend/cf-ask
Any agent
npx skills add dinhanhthi/coding-friend --skill cf-ask
Clone the repo
git clone --depth 1 https://github.com/dinhanhthi/coding-friend

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 cf-ask

README.md
[![agentmods](https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-ask.svg)](https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-ask)
Your own site
<a href="https://agentmods.dev/skills/dinhanhthi/coding-friend/cf-ask"><img src="https://agentmods.dev/badge/skills/dinhanhthi/coding-friend/cf-ask.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,927 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00068 $0.02927
Opus 5 $0.00034 $0.01463
Sonnet 5 $0.00014 $0.00585
Haiku 4.5 $0.00007 $0.00293

Measured 4d ago against content hash cf5c8b5320f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cf-ask scanned grade A with 0 findings 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 4d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin-antigravity/skills/cf-ask/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/cf-ask

CLI Requirement: OPTIONAL — Uses the memory MCP from coding-friend-cli for fast indexed search and storage. Without the CLI: falls back to grep over docs/memory/ and direct file writes. Full functionality preserved, slower memory recall. See CLI requirements.

Answer the question: $ARGUMENTS

Purpose

Quick, focused Q&A about the codebase. Proactively explores code to find the answer, then saves the Q&A to project memory so it can be referenced later.

  • Unlike /cf-research: single focused answer, no multi-doc output
  • Unlike /cf-remember: proactively explores the codebase to answer vs extracting knowledge already in conversation

Folder

Output goes to {docsDir}/memory/ (default: docs/memory/). Check .coding-friend/config.json for custom docsDir if it exists.

IMPORTANT — path resolution:

  • Use MAIN_REPO_ROOT from the SessionStart bootstrap context (injected via session-init.sh). If absent, fall back to running pwd for $CWD and use $CWD as MAIN_REPO_ROOT.
  • Read config from CF_CONFIG_FILE (= $MAIN_REPO_ROOT/.coding-friend/config.json) — do NOT search sub-folders
  • Use CF_DOCS_ROOT as the docs base dir (= $MAIN_REPO_ROOT/{docsDir} where docsDir comes from config, default docs)
  • Always resolve file_path as an absolute path: {CF_DOCS_ROOT}/memory/{category}/{name}.md
  • Never use relative paths in write specs — they may resolve incorrectly when the working directory contains nested git repos

Workflow

Step 0: Custom Guide

Custom guide — auto-loaded below (if the raw command shows instead of its output, run it yourself):

bash "<plugin-root>/lib/load-custom-guide.sh" cf-ask

If output is not empty, integrate returned sections: ## Before → before first step, ## Rules → apply throughout, ## After → after final step.

Step 1: Parse the Question

  1. Read $ARGUMENTS as the question
  2. If no question provided, ask the user what they want to know
  3. Identify keywords and likely relevant areas (modules, features, patterns)
  4. Classify the question type — check if the question is a flow question. A flow question asks about how something works end-to-end, how components interact, or what happens when a process runs. Trigger words: "how does X work", "flow of", "lifecycle", "sequence", "process", "when X happens", "walk me through", "how are X connected", "what triggers", "what happens when", "pipeline", "chain". Non-flow questions (lookup/definition/pattern/why) do NOT trigger this path.

Read the full file on GitHub · 285 lines

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. 4d ago First seen · 285 lines · 68 tokens per session scan A cf5c8b5320f3

Subscribe to this mod's changes

cf-ask is a skill published in the GitHub repository dinhanhthi/coding-friend (3 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 2,927 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

persist-memory

Persist information to long-term memory at /.clacky/memories/. Use when the user asks you to remember/note something, or when reviewing a finished conversation for facts worth keeping. Handles file naming, topic merging, frontmatter, and size limits.

clacky-ai/openclacky · 54 tokens

recall-memory

Recall relevant long-term memories on demand. Given a topic or question, judges relevance from pre-loaded metadata, loads only relevant files, and returns a concise summary to the main agent.

clacky-ai/openclacky · 40 tokens

doris-debug-resource-isolation

Use for Doris Workload Group / resource tag queue starvation, CPU/memory isolation leaks, and workload policy debugging. Commands: SHOW WORKLOAD GROUPS, EXPLAIN resource.

apache/doris-skills · 43 tokens

acontext-installer

Install Acontext, Login & Init Acontext Project, Add Skill Memory to Agent.

memodb-io/Acontext · 22 tokens

campaign-operations-knowledge-builder

将活动目标、用户路径、渠道分工、物料资产、时间节奏、风险预案和复盘结论等资料,整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的运营类知识库。适用于用户要求“整理活动 / Campaign 运营知识库”“沉淀运营 SOP”“把运营资料变成项目资料”“维护运营知识库”的场景。.

limecloud/lime · 99 tokens

organization-knowhow-knowledge-builder

将团队 SOP、交付流程、角色职责、项目复盘、FAQ、决策边界和升级机制,整理成符合 Agent Knowledge v0.6 document-first 标准、可被 AI 安全调用的组织经验知识库。适用于用户要求“整理组织知识库”“沉淀团队 SOP”“把交付经验变成项目资料”“维护组织 know-how”的场景。.

limecloud/lime · 92 tokens