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 ilang-ai/autocode --skill shipgit clone --depth 1 https://github.com/ilang-ai/autocodeWrote 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/ilang-ai/autocode/ship)<a href="https://agentmods.dev/skills/ilang-ai/autocode/ship"><img src="https://agentmods.dev/badge/skills/ilang-ai/autocode/ship/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/ilang-ai/autocode/ship"><img src="https://agentmods.dev/badge/skills/ilang-ai/autocode/ship.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01141 |
| Opus 5.5 | $0.00000 | $0.00456 |
| Sonnet 5.5 | $0.00000 | $0.00228 |
| Haiku 4.5 | $0.00000 | $0.00114 |
Grade A, and why
ship 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ship — S6: the end is a URL
[PROTOCOL:iLang|v=5.0|layer=declaration]
::PRIOR{dimension:deploy_target|default:static_zero_cost_pages|authority:system|scope:@MVP} ::PRIOR{dimension:completion|default:not_live_until_url_opened_and_acceptance_rerun|authority:system|scope:@JOURNEY}
::GENE{ship|conf:confirmed|scope:global} T:scan_secrets_first|tool:scripts/scan-secrets.sh|block_if_found T:ai_picks_the_target|static⇒github_pages_zero_cost|serverless⇒workers|backend_or_db⇒server|say_why_in_one_sentence T:default_target=static_zero_cost_pages|when:no_backend|tool:scripts/go_live_pages.py T:upgrade_to_server|when:backend_or_db_needed|ask_cost_once T:detect_account_state|logged_in|account_no_login|no_account|tool_missing T:no_account⇒three_line_signup_guide|come_back_and_say_done T:login_is_device_code_in_their_browser|password_or_token_never_passes_through T:tool_missing⇒install_it_yourself|one_line_notice T:one_question=site_and_files_will_be_public T:server_path|code_already_on_the_server|start_service|nginx|verify_then_show_url T:poll_until_built|open_url|check_ssl|check_mobile_loads|rerun_acceptance_on_live_html T:domain_optional|recommend_one_registrar|guide_every_click|dns_and_ssl_automatic|verify_resolves T:move_files_to_the_server_yourself|guide_scp_only_when_you_cannot T:say_the_url_in_one_line|then_celebrate_in_one_line A:deploy_before_secret_scan⇒scan_first A:ask_user_where_to_deploy⇒pick_for_them A:say_its_live_without_opening_the_url⇒verify_first A:verify_the_local_file_instead_of_the_live_page⇒fetch_live A:paste_tokens_or_passwords⇒never|device_flow_only A:assume_user_knows_dns_or_scp⇒explain_simply A:skip_ssl⇒always_https A:end_with_a_file_path⇒end_with_the_url
::ACTIVATE{ship} ON:build_complete ON:S5-verify.all_match ON:before_deploy ON:deploy_complete ON:user_asks_about_domain
::STATE{@URL, the public address}
[CHEK:@SITE|typ=secret_scan]=>[DECI:@TARGET|typ=static_or_server]=>[DPLO:@SITE|dst=@URL|scp=public]=>[CHEK:@URL|whr=http_200_and_rules_block]=>[TEST:@ACCEPT|src=@URL]=>[Ω:@USER|fmt=text|lim=2]
::EVIDENCE{id:s1|deliverable:url|kind:http|ref:live_url|verified_by:@TOOL|result:200_and_rules_block} ::FALLBACK{stage:S6-ship|when:no_github_account|do:signup_guide_then_device_login|never:handle_password} ::FALLBACK{stage:S6-ship|when:hosting_api_fails|do:retry_then_exact_clicks_in_their_browser} ::FALLBACK{stage:S6-ship|when:mvp_needs_backend|do:upgrade_to_server_target|ask:cost_once} ::FALLBACK{stage:S6-ship|when:live_page_differs_from_local|do:fix_cache_path_case|rerun_live_acceptance}
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed f9390816afc9
- 11d ago Changed 00e9b637f5a4
- 12d ago First seen · 71 lines · 0 tokens per session scan A 49d40b5dd800
ship is a skill published in the GitHub repository ilang-ai/autocode (104 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,141 tokens. 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 2026-10-15.
Other skills, from other repositories
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
distributed-training-ray-train
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
infrastructure-skypilot
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
distributed-training-deepspeed
Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention.
inference-serving-tensorrt-llm
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
infrastructure-modal
Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling.