Borrowing it
Nothing to install: this file belongs to fold-run/fold. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fold-run/fold/main/.claude/skills/ship/SKILL.mdgit clone --depth 1 https://github.com/fold-run/foldWrote 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/fold-run/fold/ship)<a href="https://agentmods.dev/skills/fold-run/fold/ship"><img src="https://agentmods.dev/badge/skills/fold-run/fold/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/fold-run/fold/ship"><img src="https://agentmods.dev/badge/skills/fold-run/fold/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 | $0.00074 | $0.01241 |
| Opus 5.5 | $0.00030 | $0.00496 |
| Sonnet 5.5 | $0.00015 | $0.00248 |
| Haiku 4.5 | $0.00007 | $0.00124 |
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 2mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipping a change in fold
/preflight decides whether a diff is ready. This lands it. /watch-ci
triages what CI says back. Every substantive change since #63 has merged
through a squashed PR — nothing but a release commit goes straight to main.
1. Gate before branching
Run /preflight first, and do not open a PR on an unverified diff. A red
PR costs a round trip; the gate costs a few minutes and runs locally.
2. Branch: type/slug
feat/, fix/, docs/, chore/ — a short hyphenated slug after it.
feat/downstream-keepalive, fix/console-sync-weekly-force-push,
docs/protocol-era-transition.
The prefix survives even though the title will not have one. The branch name is where the change gets classified; the title is where it gets explained.
3. The title is a prose sentence naming the problem
This is the convention that is easiest to get wrong, because it is the opposite of the usual advice and CONTRIBUTING said otherwise until it was corrected.
A PR title states the defect or the behavior, in a full sentence, with no
area: prefix. Real ones:
- A retry answering an upstream's question arrived looking like a first try
- Every federated list was announcing a cache scope that does not exist
- The weekly console bump has been force-pushing a branch it cannot see
- A client had to be refused before it could learn what to ask for
- Three things the gateway was letting past it
Not fix: forward MRTR continuation — that is the branch name's job, and
it says what the diff does rather than what was wrong.
The test: a reader who knows fold should feel the problem land. A title that describes the change instead of the defect is a changelog line.
Commits that go straight to main keep the area: prefix — release: v1.15.0, docs: repoint the conformance receipt at the v1.14.0 run.
Those are housekeeping with no problem to name.
Merges are squashed, so GitHub appends (#N) and the title becomes the
commit subject verbatim. Write it to read well in git log.
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.
- 2mo ago First seen · 114 lines · 74 tokens per session scan A 17a19943d022
ship is a skill published in the GitHub repository fold-run/fold (1 stars, last pushed 12d ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,241 once invoked, about $0.0003 per session on Opus 5.5. 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.
ship compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| shipfold-run/fold | Skill | 1 | 12d ago | Apache-2.0 | A | 74 | Claude Code |
| vhs-e2e-gifdimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 106 | Claude Code, Codex |
| check-linters-before-commitdimetron/pi-go | Skill | 222 | 3d ago | MIT | A | 30 | Claude Code, Codex |
| gh-labelsUnique-Divine/jiyuu | Skill | 6 | yesterday | MIT | A | 98 | Claude Code, Codex |
| gh-prUnique-Divine/jiyuu | Skill | 6 | yesterday | MIT | A | 63 | Claude Code, Codex |
| gh-revUnique-Divine/jiyuu | Skill | 6 | yesterday | MIT | A | 89 | Claude Code, Codex |
| gh-ci-watchUnique-Divine/jiyuu | Skill | 6 | yesterday | MIT | A | 74 | Claude Code, Codex |