semantic-anchor-onboarding

semantic-anchor-onboarding is a skill for Claude Code from LLM-Coding/Semantic-Anchors. It costs 63 tokens per session (370 once invoked), scanned A, original, Apache-2.0.

A deprecated name for the semantic-contracts-installer skill, which adds shared project instructions from predefined templates. It can also preserve the older mode that installs only semantic anchor blocks.

In plain words
What is it for?
Use semantic-contracts-installer instead when installing semantic contracts or the older anchor blocks into a project’s instruction files.
Why use it?
It tells you the name has changed and helps prevent starting new work with an alias that will be removed after one release.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the semantic-anchors plugin — 6 skills shipped together

Good fit Use semantic-contracts-installer instead when installing semantic contracts or the older anchor blocks into a project’s instruction files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/llm-coding/semantic-anchors/semantic-anchor-onboarding
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 LLM-Coding/Semantic-Anchors --skill semantic-anchor-onboarding
Clone the repo
git clone --depth 1 https://github.com/LLM-Coding/Semantic-Anchors

Made for: Claude Code.

Or install semantic-anchors, the plugin that ships this one along with the rest of its 6 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 semantic-anchor-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/llm-coding/semantic-anchors/semantic-anchor-onboarding.svg)](https://agentmods.dev/skills/llm-coding/semantic-anchors/semantic-anchor-onboarding)
Your own site
<a href="https://agentmods.dev/skills/llm-coding/semantic-anchors/semantic-anchor-onboarding"><img src="https://agentmods.dev/badge/skills/llm-coding/semantic-anchors/semantic-anchor-onboarding.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 370 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00063 $0.00370
Opus 5 $0.00032 $0.00185
Sonnet 5 $0.00013 $0.00074
Haiku 4.5 $0.00006 $0.00037

Measured 8d ago against content hash 0baa0c974098, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

semantic-anchor-onboarding 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 8d 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.

plugins/semantic-anchors/skills/semantic-anchor-onboarding/SKILL.md · 29 lines

What it actually says

Semantic Anchor Onboarding (deprecated)

This skill has been renamed to semantic-contracts-installer. The repositioning reflects the project's Anchor/Contract/Skill taxonomy (ADR-007): a bare list of anchors is something the model already knows, while a contract (a named composition of anchors plus a project-local template) is the part it cannot guess — so installing contracts is the high-value job.

What to do

Use the semantic-contracts-installer skill instead. It:

  • installs Semantic Contracts (renders their templates into the project's instruction file) as the default mode,
  • keeps the former anchor-block behavior as a --anchors-only sub-mode,
  • recognises and idempotently overwrites any block this old skill left (same <!-- semantic-anchors:start/end --> markers),
  • only installs a Claude SessionStart hook for files Claude Code does not load natively (no hook for CLAUDE.md), with matcher startup.

No migration step is required: point your workflow at semantic-contracts-installer and run it; it replaces the existing marker block in place.

This alias will be removed after one release.

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. 8d ago First seen · 29 lines · 63 tokens per session scan A 0baa0c974098

Subscribe to this mod's changes

semantic-anchor-onboarding is a skill published in the GitHub repository LLM-Coding/Semantic-Anchors (465 stars, last pushed 6d ago), licensed Apache-2.0. It adds 63 tokens to every session and 370 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 2026-08-30.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens