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 firatcand/forge --skill shipgit clone --depth 1 https://github.com/firatcand/forgeWrote 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/firatcand/forge/ship)<a href="https://agentmods.dev/skills/firatcand/forge/ship"><img src="https://agentmods.dev/badge/skills/firatcand/forge/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/firatcand/forge/ship"><img src="https://agentmods.dev/badge/skills/firatcand/forge/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 | $0.00029 | $0.01235 |
| Opus 5.5 | $0.00012 | $0.00494 |
| Sonnet 5.5 | $0.00006 | $0.00247 |
| Haiku 4.5 | $0.00003 | $0.00123 |
Grade A, and why
ship scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ship
Preflight: worktree guard
Task-scoped mutating skill — must run from a worktree, not the main checkout. Contract: skills/_shared/worktree-guard.md.
TOPLEVEL="$(git rev-parse --show-toplevel 2>/dev/null || echo '')"
if [ -z "$TOPLEVEL" ]; then
echo "✗ worktree-guard: not inside a git repository" >&2
exit 1
fi
BRANCH="$(git branch --show-current 2>/dev/null || echo '')"
DEFAULT_BRANCH="$(git symbolic-ref --short refs/remotes/origin/HEAD 2>/dev/null | sed 's@^origin/@@' || echo 'main')"
if [ -f "$TOPLEVEL/.forge/worktree-task.json" ]; then
echo "✓ worktree-guard: $TOPLEVEL ($BRANCH)"
elif [ "$BRANCH" = "${DEFAULT_BRANCH:-main}" ]; then
echo "✗ worktree-guard: refusing to run on default branch '$BRANCH' from $TOPLEVEL" >&2
echo " Parallel Claude Code sessions on the main checkout clobber each other's HEAD." >&2
echo " → cd into an existing worktree, or run /pickup-task to create one." >&2
exit 1
else
echo "⚠ worktree-guard: no .forge/worktree-task.json at $TOPLEVEL (branch: $BRANCH)" >&2
echo " Proceeding, but this worktree may be manually-created or stale." >&2
fi
SPEC-changes signal (informational — never blocks the ship)
After the worktree guard and before the gates, surface whether spec/ changed
since THIS task was claimed (FORGE-164 — the push-time half of the FORGE-114
mitigation). This is strictly informational: it NEVER blocks the ship; it just
makes a stale-claim risk visible in the PR.
# TASK_ID is the current task (from .forge/worktree-task.json).
forge orchestrate spec-diff "$TASK_ID" --json
- If the
datafield is non-null (commits touchingspec/landed since the claim), do two things:- Print the rendered block to the operator.
- Add a
### ⚠ SPEC changes since this task was claimedsection to the PR body (see the template below) listing the commit summaries, plus a pointer toforge orchestrate spec-diff --all-activefor OTHER affected tasks.
- If
datais null, omit the section entirely — no SPEC drift to report.
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.
- 1mo ago First seen · 103 lines · 29 tokens per session scan A 894beb09100f
ship is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,235 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
git-ops
Git workflow assistance for managing branches, worktrees, commits, rebases, releases, and pull or merge requests. Git is a tool for tracking code changes; a pull request or merge request proposes changes for review.
monitor
Reconcile local branches/worktrees with GitHub/GitLab PR/MR lifecycle, clean finished worktrees, or configure recurring reconciliation. Use for lifecycle sweeps and ongoing PR/MR monitoring. For a one-time PR/MR status query, use git-ops.
gcampr
Commit current changes, push, and create/reuse a pull/merge request (GitHub PR or GitLab MR). Use when the user says "gcampr" or asks to commit + push + open/raise a PR / MR / pull request / merge request.
release
Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASERULE.md, then guides the release.
gsd-complete-milestone
Archive completed milestone and prepare for next version.
codex-issue-coordinator
Coordinates a large batch of GitHub issues through separate Codex worker threads, tested pull requests, review loops, and gated merges. Use when the user asks one Codex thread to manage several coding sessions or complete a parent issue, milestone, or issue batch.