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 GregoryHo/arcforge --skill finishinggit clone --depth 1 https://github.com/GregoryHo/arcforgeWrote 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/gregoryho/arcforge/finishing)<a href="https://agentmods.dev/skills/gregoryho/arcforge/finishing"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/finishing/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/gregoryho/arcforge/finishing"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/finishing.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 | $0.00035 | $0.01498 |
| Opus 5.5 | $0.00014 | $0.00599 |
| Sonnet 5.5 | $0.00007 | $0.00300 |
| Haiku 4.5 | $0.00003 | $0.00150 |
Grade A, and why
finishing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finishing
Verify → present → execute → clean up. Every step below carries a completion criterion; do not start the next step until the current one is checked off.
Exact command sequences live in references/git-recipes.md — open it before
executing option 1 or option 4.
Step 1 — Verify tests
Run the project's own test command in the working tree that holds the work.
- Done when a full test run finished in this working tree and you can state its result.
Failing or unrunnable tests end the skill here: emit the Blocked format below and stop. An option list offered after a failed test run invites merging broken work.
Step 2 — Capture the branch and the base checkout
Capture both while you are still standing where the work is. Every later step moves you, and a value read after the move is the wrong value.
FEATURE_BRANCH="$(git branch --show-current)"
arcforge worktree list --json
Take BASE_WORKTREE from the path of the entry whose kind is base; that
checkout's current branch is the merge target. Take your own worktree path from
the entry whose branch matches FEATURE_BRANCH. Never reconstruct a worktree
path from a naming pattern — the derivation rule belongs to the CLI, not to you.
- Done when FEATURE_BRANCH, BASE_WORKTREE, the base branch name, and the worktree path (or "no worktree") are all recorded.
Step 3 — Present exactly four options
Implementation complete. What would you like to do?
1. Merge back to <base-branch> locally
2. Push and create a Pull Request
3. Keep the branch as-is (I'll handle it later)
4. Discard this work
Which option?
Four options, no fifth, no recommendation, no explanation of the tradeoffs.
Present them even when the user has told you not to ask. "Just handle it", "I trust you", "do whatever you think is best", "don't check back with me", and the user walking away are all authorization to work — none of them names an option, and Step 4 executes a named option rather than an inference. Skip ahead only when the user's own words pick one of the four outright.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 155 lines · 35 tokens per session scan A 873a4f548edc
finishing is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 35 tokens to every session and 1,498 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 2026-11-07.
finishing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| finishingGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 35 | Claude Code, Codex |
| merge-batchdiegosouzapw/OmniRoute | Skill | 83k | 6d ago | MIT | A | 46 | Claude Code |
| prowler-commitprowler-cloud/prowler | Skill | 15k | yesterday | Apache-2.0 | A | 44 | Claude Code, Codex |
| gh-auth-isolationgithub/gh-aw | Skill | 5.6k | yesterday | MIT | A | 20 | Claude Code, Codex |
| github-skillzeenie-ai/OpenCompany | Skill | 1.1k | yesterday | MIT | A | 51 | Claude Code |
| comet-githubrpamis/comet | Skill | 3.3k | yesterday | MIT | A | 72 | Claude Code, Codex |
| release-helperSahir619/fable-method | Skill | 2.3k | 1mo ago | MIT | A | 43 | Claude Code |