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 skills/conn-castle/agent-layer/ship-prnpx skills add conn-castle/agent-layer --skill ship-prgit clone --depth 1 https://github.com/conn-castle/agent-layerWrote 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/conn-castle/agent-layer/ship-pr)<a href="https://agentmods.dev/skills/conn-castle/agent-layer/ship-pr"><img src="https://agentmods.dev/badge/skills/conn-castle/agent-layer/ship-pr.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 | $0.00028 | $0.00903 |
| Opus 5 | $0.00014 | $0.00451 |
| Sonnet 5 | $0.00006 | $0.00181 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
ship-pr 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 today.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ship-pr
Invoking this skill authorizes branch creation, staging, commits, pushes, PR creation or updates, and eligible comment replies needed to prepare one PR for merge. It does not authorize the merge itself.
If references/repo-specific-pr-policy.md exists, read it before starting the
workflow and treat it as authoritative.
Inputs
Require a pr_worker dispatch target and use /dispatch-agent for every
dispatch. Relay any additional caller input in every pr_worker prompt.
Unless the user narrows the scope, include the entire current working tree.
Workflow
-
Create a branch when repository norms require one. Commit the intended changes, push, and create or reuse the PR. Derive its title from the changes and fill
assets/pr-body-template.md, removing unused sections and placeholders. -
Start one watcher in a managed background session. Keep it running until the PR merges or the workflow stops, then stop it. If it exits after a transient transport failure, refetch authoritative state and restart it with the same append-only log.
bash <skill_dir>/scripts/watch-pr-events.sh \ --repo <owner/name> \ --pr <pr-number> \ --log-file .agent-layer/tmp/ship-pr-events-<pr-number>.jsonl \ --interval-seconds 300 -
Fetch the current head, checks, and mergeability with
gh. Read comments with this stateless command; never infer current state from the watcher log:bash <skill_dir>/scripts/read-pr-comments.sh \ --repo <owner/name> \ --pr <pr-number>Dispatch
pr_workerfor unresolved feedback with the exact PR, head, andreferences/address-pr-comments.md; for a failed required check, also provide its evidence andreferences/fix-ci.md. The worker edits the local tree but does not commit, push, or post replies. Resolve mechanical conflicts automatically.The PR is ready to merge only when:
- The PR is mergeable at its latest head.
- At least one agent or human reviewer has posted feedback as a formal review or comment.
- Every required check and repository gate is green.
- Every eligible comment has a validated reply.
- If the optional repository policy exists, every merge criterion it defines is met.
What ships with it
5 files 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.
- today Changed · +5 lines 49cd98731e52
- 4d ago First seen · 91 lines · 28 tokens per session scan A 85a1f5a1a739
ship-pr is a skill published in the GitHub repository conn-castle/agent-layer (10 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 903 once invoked, about $0.0001 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
gtplanner
使用 GTPlanner 生成项目规划和技术架构文档。当用户需要： (1) 生成 PRD 或产品需求文档 (2) 规划项目架构 (3) 技术选型和推荐 (4) 创建详细设计文档 (5) 分析项目可行性 时触发此 skill。支持中英日西法五种语言。 触发词："PRD"、"项目规划"、"架构设计"、"技术方案"、"设计文档"。.
dividend-analysis
Comprehensive capital allocation analysis: dividends, buybacks, M&A, debt management, and FCF deployment.
position-ladder
Plan a staged position — entry ladder, share-count floor/ceiling, and the trim/re-add cycle that lowers average cost — with lot accounting, wash-sale checks, total-return honesty, and a thesis-break exit gate.
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.
stock-eval
Evaluate US stocks with comprehensive fundamental and valuation analysis.
stock-valuation
Multi-method stock valuation using DCF, comparable company analysis, EV multiples, and residual income models.