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/firatcand/forge/wrap-upnpx skills add firatcand/forge --skill wrap-upgit 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/wrap-up)<a href="https://agentmods.dev/skills/firatcand/forge/wrap-up"><img src="https://agentmods.dev/badge/skills/firatcand/forge/wrap-up.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 | $0.00056 | $0.01520 |
| Opus 5 | $0.00028 | $0.00760 |
| Sonnet 5 | $0.00011 | $0.00304 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
wrap-up 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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/wrap-up
Run this once a task's PR has merged. It tears down the per-task workspace and
returns you to a clean main. It is the inverse of /pickup-task.
Skill ↔ verb contract: this skill owns the UX (scope detection, the merged
gate, previews, confirmations, branch deletion, the main fast-forward). The
worktree removal itself goes through the verb — forge orchestrate gc --remove-worktrees — which owns the eligibility + lease state machine. The
skill NEVER removes a worktree directory by hand and NEVER mutates orchestrator
state directly.
Modes:
- default — wrap up a single task (the one whose worktree you are in, or one you pick from the candidate list).
--all— batch: wrap up every terminal-state task with a merged PR, behind a single confirmation.
Safety contract (do not drop these clauses)
These four gates are non-negotiable. A future edit must keep every one.
Unmerged-abort gate
The PR-merged check runs BEFORE anything is deleted. If gh pr view reports the
branch's PR is not MERGED, abort immediately — NOTHING is deleted (no
worktree removal, no branch deletion, no main switch). An open or closed-
unmerged PR means the work is not done; wrapping up would orphan it.
Confirmation-before-destruction gate
Worktree removal and branch deletion only run after an explicit user
confirmation. Preview the full plan first (worktree path, branch, main delta).
Suggest-don't-force: never delete on the same turn you discovered the candidate.
In --all mode a SINGLE batched confirmation covers the whole list, shown in
full before the prompt.
ff-only refusal on dirty main
Before git switch main && git pull --ff-only, run git status --porcelain in
the main checkout. If it is non-empty, refuse the pull and show the porcelain
output verbatim so the user can see exactly what is dirty. Never stash, reset,
or force. --ff-only itself refuses any non-fast-forward; do not override it.
-D second-confirm
git branch -d <branch> (safe delete) is the default. It fails if the branch is
not fully merged into its upstream. Only escalate to git branch -D (force) after
a SECOND explicit confirmation — and only after the PR-merged gate has already
passed. A -d failure after a merged PR usually means the merge was a squash or
rebase; surface that, then offer the -D path.
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.
- 4d ago First seen · 159 lines · 56 tokens per session scan A 8db3e98bcdf4
wrap-up is a skill published in the GitHub repository firatcand/forge (13 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 1,520 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
prospec-knowledge-generate
Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.
submit-pr
Open a prospec pull request in the house format — push the change's two commits, write the Traditional Chinese body, and link it to its issue. Triggers: submit pr, open pr, 開 PR, 送 PR, 發 PR, pull request, 提交 PR.
submit-issue
Open a prospec GitHub issue in the house format — conventional-commit title, Traditional Chinese body (problem → solutions → acceptance criteria), downstream-compatibility block, series cross-links, and optional model-routing guidance. Triggers: submit issue, open issue, create issue, file issue, 開 issue, 發 issue, 建…
prospec-explore
Explore - Requirement exploration, problem investigation, and solution comparison partner. Triggers: explore, compare, investigate, unsure, clarify, 探索, 比較, 釐清, 調查, 不確定.
prospec-plan
Plan Implementation - Convert User Story into technical implementation plan (plan.md) and change specification (delta-spec.md). Triggers: plan, architecture, technical plan, 規劃, 架構規劃, 技術規劃.