crier

crier is a skill for Claude Code from queelius/claude-anvil. It costs 39 tokens per session (975 once invoked), scanned A, original, MIT.

A cross-posting workflow for adapting one blog article to several social platforms. The blog remains the original source, while the content is adjusted to fit each platform’s style and limits.

In plain words
What is it for?
Use it to prepare and publish blog content on Dev.to, Hashnode, Bluesky, Mastodon, Medium, Twitter, Threads, and LinkedIn.
Why use it?
It avoids rewriting and publishing the same article manually for every platform, while accounting for differences such as character limits and posting methods.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the crier plugin — 1 skill, 2 commands, 2 agents, 1 MCP server shipped together

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/queelius/claude-anvil/crier
Any agent
npx skills add queelius/claude-anvil --skill crier
Clone the repo
git clone --depth 1 https://github.com/queelius/claude-anvil

Made for: Claude Code.

Or install crier, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 2 agents, 1 MCP server.

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 crier

README.md
[![agentmods](https://agentmods.dev/badge/skills/queelius/claude-anvil/crier.svg)](https://agentmods.dev/skills/queelius/claude-anvil/crier)
Your own site
<a href="https://agentmods.dev/skills/queelius/claude-anvil/crier"><img src="https://agentmods.dev/badge/skills/queelius/claude-anvil/crier.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 975 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 5.1 $0.00039 $0.00975
Opus 5 $0.00019 $0.00487
Sonnet 5 $0.00008 $0.00195
Haiku 4.5 $0.00004 $0.00097

Measured 5d ago against content hash 4241ffd918ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

crier 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 5d 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.

crier/skills/crier/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crier Cross-Posting

Crier cross-posts blog content to multiple platforms. The blog is the source of truth.

Division of labor:

  • Crier MCP tools handle mechanics: publish, track, query, validate
  • Claude handles judgment: rewrites, platform voice, user interaction

Platform Reference

Platform Mode Limit Short-form? Notes
devto API none No Tags auto-sanitized
hashnode API none No
bluesky API 300 Yes Needs rewrite
mastodon API 500 Yes Needs rewrite
medium import none No User imports from canonical URL
twitter paste 280 Yes Copy-paste only
threads paste 500 Yes Copy-paste only
linkedin paste 3000 No Copy-paste only

Rewrite Guidelines

When cross-posting to short-form platforms (bluesky, mastodon), write a rewrite and pass it via crier_publish(rewrite_content=...).

Rules

  1. Lead with insight, not summary. Open with the most interesting idea.
  2. No meta-language. Don't say "New blog post" or "I wrote about."
  3. Crier appends the canonical URL automatically. Never include it in the rewrite.
  4. Match platform voice:
    • Bluesky: conversational, personal, like talking to a friend
    • Mastodon: slightly more formal, technical audience
  5. Budget for the appended URL. Crier appends \n\n<canonical URL> to the rewrite and then enforces the platform limit on the combined text, so the real budget is limit - (URL length + 2): roughly 230 chars on Bluesky (limit 300) and 430 on Mastodon (limit 500) for typical metafunctor URLs. Over-budget rewrites fail at the confirmed publish step, not at preview.

Read the full file on GitHub · 86 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. 5d ago First seen · 86 lines · 39 tokens per session scan A 4241ffd918ad

Subscribe to this mod's changes

crier is a skill published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 975 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.

Related

Other skills, from other repositories