anchor

anchor is a command for coding agents from xcodethink/open-claude-code-skills. It costs 30 tokens per session (337 once invoked), scanned A, original, MIT.

A conversation-starting checklist that confirms which project you are working on, its current state, your goal, and its constraints before changes begin.

In plain words
What is it for?
Use it at the start of a task, when switching projects, or when you need approval before each operation.
Why use it?
It prevents an agent from guessing the project or acting in the wrong one. It also pauses before edits or shell commands until the required context is confirmed.

Command

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 commands/xcodethink/open-claude-code-skills/anchor
Clone the repo
git clone --depth 1 https://github.com/xcodethink/open-claude-code-skills

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 anchor

README.md
[![agentmods](https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/anchor.svg)](https://agentmods.dev/commands/xcodethink/open-claude-code-skills/anchor)
Your own site
<a href="https://agentmods.dev/commands/xcodethink/open-claude-code-skills/anchor"><img src="https://agentmods.dev/badge/commands/xcodethink/open-claude-code-skills/anchor.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 337 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 $0.00030 $0.00337
Opus 5 $0.00015 $0.00169
Sonnet 5 $0.00006 $0.00067
Haiku 4.5 $0.00003 $0.00034

Measured 4d ago against content hash 9514f2074982, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anchor 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.

commands/anchor.md · 25 lines

What it actually says

anchor — 新对话开场 / 项目锚定

用户输入 /anchor $ARGUMENTS 触发 项目锚定四要素(防猜项目 / 防 4-08 跨项目误删事故)。

立刻读取并完整加载: ~/.claude/prompts/lib/09-元指令/新对话锚定.md

按其"行为契约"段严格执行:

  1. 未拿到 4 项前禁止动手:项目 + 当前状态 + 本次目标 + 约束红线
  2. 4 项齐全后复述确认 + 列推进步骤,等用户 yes
  3. 本次目标命中关键词时主动建议叠加关联模板(加 X → safe-add / 部署 → deploy / 修 bug → fix-bug 或 stuck-bug)

参数含修饰符:

  • 快锚定 → 切 B 模式 2 项问(严肃任务自动升回完整)
  • 操作前必问 → 锚定后每步等 yes

核心契约:猜项目踩坑成本远大于锚定 30 秒。4 项齐全前禁止 Edit/Write/Bash 修改类工具。

参数: $ARGUMENTS

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 · 25 lines · 0 tokens per session scan A 9514f2074982

Subscribe to this mod's changes

anchor is a command published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 30 tokens to every session and 337 once invoked, about $0.0002 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.