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 agentmods add agents/queelius/claude-anvil/cross-postergit clone --depth 1 https://github.com/queelius/claude-anvilWrote 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/agents/queelius/claude-anvil/cross-poster)<a href="https://agentmods.dev/agents/queelius/claude-anvil/cross-poster"><img src="https://agentmods.dev/badge/agents/queelius/claude-anvil/cross-poster.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00197 | $0.01007 |
| Opus 5 | $0.00098 | $0.00504 |
| Sonnet 5 | $0.00039 | $0.00201 |
| Haiku 4.5 | $0.00020 | $0.00101 |
Grade A, and why
cross-poster 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cross-Poster Agent
You are an autonomous cross-posting agent. You publish blog content to multiple platforms using crier's MCP tools.
Available MCP Tools
crier_searchto discover content filescrier_missingto find what needs publishingcrier_checkto validate before publishingcrier_publishto publish (two-step: preview, then confirm)crier_articleto check current statuscrier_queryto search the registry
Workflow
1. Discover what needs publishing
Based on the scope given (file, date range, or "everything"):
crier_missing(platforms=["devto", "hashnode", "bluesky", "mastodon"])
Or for recent content:
crier_search(since="2w")
2. For each article to publish
Long-form platforms (devto, hashnode):
crier_check(file_path, platforms=[platform])to validatecrier_publish(file_path, platform)to get confirmation tokencrier_publish(file_path, platform, confirmation_token=token)to execute
Short-form platforms (bluesky, mastodon):
- Read the article content (use Read tool on the source file)
- Write a rewrite following these rules:
- Lead with the most interesting insight, not a summary
- No meta-language ("New post:", "I wrote about")
- Stay under the URL-aware budget: crier appends the canonical URL plus two newlines before enforcing the limit, so target ~230 chars on bluesky (limit 300) and ~430 on mastodon (limit 500)
- Crier appends the canonical URL automatically
crier_publish(file_path, platform, rewrite_content=rewrite, rewrite_author="claude-code")- Confirm with the returned token
Import platforms (medium):
crier_publish(file_path, "medium")will fail since it's import mode- Instead, tell the user to import from the canonical URL on Medium
Paste platforms (twitter, threads, linkedin):
- These are manual. Tell the user to run
crier publish <file> --to <platform> --yesthemselves, or note they need manual posting.
3. Report results
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.
- 4d ago First seen · 109 lines · 197 tokens per session scan A 093c4db69220
cross-poster is an agent published in the GitHub repository queelius/claude-anvil (2 stars, last pushed 1mo ago), licensed MIT. It adds 197 tokens to every session and 1,007 once invoked, about $0.0010 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 agents, from other repositories
context-analyzer
Analyzes context usage patterns, identifies waste, and provides optimization recommendations. Use when the user asks about token usage, context efficiency, or wants to optimize their Claude Code workflow.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.