Borrowing it
Nothing to install: this file belongs to matteocervelli/llms. 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/matteocervelli/llms/main/.claude/skills/ship/SKILL.mdgit clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/matteocervelli/llms/ship)<a href="https://agentmods.dev/skills/matteocervelli/llms/ship"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/ship.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 | $0.00071 | $0.01458 |
| Opus 5 | $0.00036 | $0.00729 |
| Sonnet 5 | $0.00014 | $0.00292 |
| Haiku 4.5 | $0.00007 | $0.00146 |
Grade A, and why
ship scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
RESULT=$(curl -s \ How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship Skill
Purpose
Zero-ceremony last mile: takes validated code (post /pre-commit) and ships it as a pull request in one shot.
Chain: commit → push → /pr-creator (artifact verification + PR creation)
Does NOT run quality checks or tests — that's /pre-commit's job.
Usage
/ship "feat: add search feature" # commit message provided
/ship --issue 42 "feat: add search feature" # links issue — PR body gets "Closes #42"
/ship --issue 42 # derive commit message from diff + branch name
/ship --issue 42 --main # direct-to-main: no PR, close issue, delete branch
--main is the "no review needed" fast-path: commit → push to main → close issue → delete branch.
Only use when the change is tiny, fully validated, and genuinely needs no review.
Workflow
1. Pre-Ship Sanity Check
git status
git diff --stat
-
If working tree is already clean (nothing to commit): skip to Step 3 (push).
-
If
/pre-commithasn't been mentioned this session, warn:"⚠ Did you run
/pre-commit?/shipassumes all checks passed. Proceed? [y/N]"
2. Commit
Derive commit type from changes if not explicit in message:
| Change type | Prefix |
|---|---|
| New functionality | feat: |
| Bug fix | fix: |
| Docs only | docs: |
| Refactor | refactor: |
| Chore / tooling | chore: |
If message not provided, generate from git diff --staged --stat + branch name.
git add -u # stage tracked changes (not untracked)
git commit -m "$(cat <<'EOF'
<type>: <description>
Closes #<N>
EOF
)"
Omit Closes #N line if no --issue flag.
3. Push
git push -u origin HEAD
If push fails (upstream diverged):
git pull --rebase origin <base-branch>
git push -u origin HEAD
SHA=$(git rev-parse HEAD)
TOKEN=$(cat ~/.config/forgejo/token)
# Wait for CI to start, then poll (max 3 attempts)
sleep 60
for i in 1 2 3; do
RESULT=$(curl -s \
-H "Authorization: token $TOKEN")
STATE=$(echo "$RESULT" | python3 -c "import json,sys; d=json.load(sys.stdin); print(d['state'])" 2>/dev/null)
[ "$STATE" = "pending" ] && sleep 30 || break
done
# Print per-job breakdown
echo "$RESULT" | python3 -c "
import json,sys; d=json.load(sys.stdin)
for s in (d.get('statuses') or []):
print(f' {s[\"context\"]}: {s[\"status\"]}')
"
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.
- 3d ago First seen · 173 lines · 71 tokens per session scan A 82ab919ab811
ship is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,458 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.