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/cratis/ai/ship-changesnpx skills add Cratis/AI --skill ship-changesgit clone --depth 1 https://github.com/Cratis/AIWhat 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 | $0.00074 | $0.03510 |
| Opus 5 | $0.00037 | $0.01755 |
| Sonnet 5 | $0.00015 | $0.00702 |
| Haiku 4.5 | $0.00007 | $0.00351 |
Grade A, and why
ship-changes 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 yesterday.
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 — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship Changes
This skill takes local modifications from the working tree and lands them on
main via a properly structured branch, commits, and PR — following all
project conventions for commits, PR descriptions, and labels. Related issue
comments and closure are separate effects; this shared skill prepares their
post-merge disposition but never assumes operation authority.
Never rewrite history while shipping. No
rebase, nocommit --amend, noreset --hard, nopush --force(or--force-with-lease), no deleting a branch that still holds unmerged commits — on any branch, including your own, unless the human asks for that exact command in that exact message. Correct a mistake with a new commit; undo withgit revert; move work withgit cherry-pick; integrate withgit merge. Do not tidy a messy series before opening the PR — the series is the record. See git-commits.md for the full prohibition and the recovery procedure.
Inputs
Collect the following before starting:
- Semantic label —
patch,minor,major, or none. Skip labeling entirely if the user says no label or omits the label. Do not ask — infer from the nature of the change or follow the user's explicit instruction. - Branch name suffix — short kebab-case description of the work, e.g.
fix/testing-orleans-runtime-assemblies. Determine from the nature of the changes if not provided. - Related GitHub issue — search read-only if the change likely relates to one; use the real number or omit the reference when none exists. Never invent or reuse example numbers. Record whether the change fully resolves or only partly addresses each issue so step 9 can prepare a no-effect disposition.
Step 1 — Review the working tree
git status
git diff
Read the full diff. Understand every changed file before touching git. Do not start staging until you know exactly how the commits will be split.
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.
- yesterday First seen · 341 lines · 74 tokens per session scan A 556c581d2f47
ship-changes is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed 4d ago), licensed MIT. It adds 74 tokens to every session and 3,510 once invoked, about $0.0004 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
ship-changes
Ship staged or unstaged local changes: create a branch, make logical commits, push to origin, open a PR with the correct description and label, merge it, close the issues it resolves, and delete the branch locally and on origin. Use whenever the user asks to commit, push, create a PR, ship, or land changes.
add-concept
Use this skill when asked to create a strongly-typed domain identifier or value (such as ProjectId, AuthorName, InvoiceNumber) in a Cratis-based project. Produces a ConceptAs record with the correct conversions and sentinel values.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
cratis-command
Step-by-step guidance for creating a Cratis Arc command — [Command] record, Handle() method, CommandValidator, proxy generation, and React .use() hook with CommandDialog. Use when adding or creating a command, wiring up a form or button to the backend, working with IEventLog, CommandResult, CommandValidator…
cratis-readmodel
Step-by-step guidance for creating a Cratis Chronicle read model from scratch — defining events, choosing between projection and reducer, [ReadModel] record with static query methods, and the generated TypeScript proxy in React. Use when creating a read model, working with [EventType], [ReadModel], IProjectionFor…
auth-and-identity
Use this skill for authentication, authorization, or identity in a Cratis Arc project — backend, frontend, or both. Covers identity providers (IProvideIdentityDetails), protecting commands/queries with authorization attributes, Microsoft Identity Platform, connecting backend identity to React, multi-tenant identity…