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.
npx skills add a2ngerer/claude_onboarding_agent --skill anchorsgit clone --depth 1 https://github.com/a2ngerer/claude_onboarding_agentWrote 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.
[](https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/anchors)<a href="https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/anchors"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/anchors/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.
<a href="https://agentmods.dev/skills/a2ngerer/claude_onboarding_agent/anchors"><img src="https://agentmods.dev/badge/skills/a2ngerer/claude_onboarding_agent/anchors.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.02338 |
| Opus 5 | $0.00023 | $0.01169 |
| Sonnet 5 | $0.00009 | $0.00468 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
anchors 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anchors — Refresh Anchor-Derived Sections
Refresh the marker sections of CLAUDE.md / AGENTS.md that were originally rendered by a setup skill from anchor content.
Ownership
This skill is the sole writer of anchor-derived marker sections (section=anchor-<slug> inside CLAUDE.md / AGENTS.md). Other skills — including /upgrade-setup — detect anchor markers but never rewrite them; they delegate any refresh to this skill. The boundary is: /upgrade-setup refreshes plugin-template-derived sections only, and /anchors refreshes anchor-derived sections only. Running /upgrade-setup never mutates anchor bodies, so a user who wants both kinds of refresh runs /upgrade-setup followed by /anchors (or just /anchors if only anchor content needs updating).
Language
Detect language from the user's first message in this invocation and respond in it throughout. All file content written to disk stays in English (repo language rule).
Argument parsing
The invocation may contain --dry-run anywhere in the argument string.
- If present: set
dry_run: true. Print diffs but write nothing. - Otherwise: set
dry_run: false.
Any other argument is ignored silently.
Pass 1 — Detect the setup
Step 1.1 — Read meta file
Read ./.claude/onboarding-meta.json if it exists. Expected shape per skills/_shared/write-meta.md.
- If the file parses and
setup_typeis a recognized slug (one of:coding,data-science,design,knowledge-base,devops,content-voice,office,research,academic-writing,web-development) → setdetected_setup: <setup_type>,meta_source: meta-file. - If the file parses and
setup_typeisgraphify→ print "/anchorshas no work to do for a standalone graphify setup — anchor sections only apply to primary setups." and exit cleanly. - If the file is missing or malformed → ask the user: "No setup detected. Which setup type does this project use? (coding, data-science, design, devops, web-development, knowledge-base, content-voice, office, research, academic-writing)". Accept any of those ten as
detected_setup. Any other reply → exit without 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.
- 10d ago First seen · 246 lines · 45 tokens per session scan A 682af3c8733c
anchors is a skill published in the GitHub repository a2ngerer/claude_onboarding_agent (5 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 2,338 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…