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 mikestankavich/claude-ship-workflow --skill workgit clone --depth 1 https://github.com/mikestankavich/claude-ship-workflowWrote 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/mikestankavich/claude-ship-workflow/work)<a href="https://agentmods.dev/skills/mikestankavich/claude-ship-workflow/work"><img src="https://agentmods.dev/badge/skills/mikestankavich/claude-ship-workflow/work.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 5.1 | $0.00000 | $0.08972 |
| Opus 5 | $0.00000 | $0.04486 |
| Sonnet 5 | $0.00000 | $0.01794 |
| Haiku 4.5 | $0.00000 | $0.00897 |
Grade A, and why
work 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 — 663 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work a ticket to a pull request
Announce at start: "Using csw:work to take to a pull request." Where the
invocation carried an editorial rider — Step 1 — echo it verbatim on that same line:
— rider: "<what they wrote>".
Invocation: $ARGUMENTS
Step 0: Read the config
csw-config json
csw-config path
If csw-config path prints nothing, this repo has no .claude/csw.json. Say so, show the
defaults you are about to use, and ask whether to continue or write a config first. Do not
silently guess a validate command.
Step 1: Resolve the ticket, the modifier, and the rider
The first token of the invocation is the ticket reference:
csw-ticket normalize "<the first token of the invocation>"
If the invocation carried no reference, ask which ticket. Do not pick one.
If normalisation exits non-zero, report its message and stop — a mistyped reference is exactly the failure this command exists to prevent.
The modifier, and then the rider
Split what is left on whitespace and consume the known modifier keywords first.
interactive is the only one this skill defines:
interactive— run superpowers:brainstorming against the ticket before the Step 5 chain. Surface the questions and wait for the answers. Do not run unattended. This is the flavour someone reaches for when the ticket is vague, or when the approach has more than one defensible shape; answering your own questions is exactly the thing it exists to prevent.- No modifier — autonomous, exactly as the rest of this skill describes. Brainstorming is skipped because the ticket is the agreed brief.
interactive changes only how the work is planned. Steps 6 through 9 are untouched: the same
validation, the same gates, the same pull request, the same hard stop. An interactive run
still ends at an open pull request and still never merges.
Then read whatever is still left over. csw:merge parses its own invocation the same way —
one grammar, both skills — and the reading is by word count:
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 · +343 lines 094a7e39ebb8
- 8d ago First seen · 320 lines · 0 tokens per session scan A 8247d51ad0b6
work is a skill published in the GitHub repository mikestankavich/claude-ship-workflow (3 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,972 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 2026-08-31.
Other skills, from other repositories
daily-working
End-to-end pipeline: pull a task from Redmine by ID, sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension (claude-in-chrome), and keep the Redmine ticket in sync throughout (in-progress…
release
Verify, sweep docs, cut a version — then hand the release sequence back.
g-update
Fix G-Forge-managed files via Step 0 staleness preflight (stops with zero writes if cache lags GitHub, directs to /plugins first), then realigns CLAUDE.md Rules, agents, architecture rules, hooks, and native pre-commit gate. Safe — G-Forge markers only.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
implement-issue
Drive a GitHub issue from branch to pull request — read the issue, create a feature branch, implement the change, run the project's build and tests, then commit, push, and open a PR. Language and build-tool agnostic. Use when asked to implement, fix, or resolve a GitHub issue by number.
cross-repo-cache
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSSREPOCACHEHIT with cached status or…