Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/andreaswasita/copilot-agents-dojonpx agentmods add skills/andreaswasita/copilot-agents-dojo/finishing-a-development-branchWrote 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/andreaswasita/copilot-agents-dojo/finishing-a-development-branch)<a href="https://agentmods.dev/skills/andreaswasita/copilot-agents-dojo/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/finishing-a-development-branch/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/andreaswasita/copilot-agents-dojo/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/andreaswasita/copilot-agents-dojo/finishing-a-development-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 131 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00019 | $0.01104 |
| Opus 5 | $0.00010 | $0.00552 |
| Sonnet 5 | $0.00004 | $0.00221 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
finishing-a-development-branch 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 12d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finishing a Development Branch Skill
Runs the closing ritual for a completed branch or worktree: final verification, full diff review, options presented to the user, chosen action executed, cleanup, and a logged retrospective. Does NOT merge without explicit user consent.
When to Use
- All tasks in
tasks/todo.mdare marked complete. - User says "merge", "we're done", "ship it", or "finish up".
- A feature branch or worktree is ready for integration.
- Ending a session that produced completed work.
Prerequisites
- All planned tasks complete with Verification Results blocks.
gitconfigured with author identity and remote access.ghCLI authenticated (for PR option).- The
powershelltool to run gates andgit. - A clean working tree.
How to Run
1. Run the dojo gate + full test suite. All green.
2. Review the full diff against main.
3. Present options: merge / PR / keep / discard.
4. Wait for the user to choose.
5. Execute the chosen action.
6. Clean up worktree, branch, and tasks/todo.md.
7. Log the retrospective in tasks/lessons.md.
Quick Reference
| Option | Commands |
|---|---|
| Merge | git checkout main && git merge --squash <branch> && git commit && git branch -d <branch> |
| PR | git push -u origin <branch> && gh pr create --fill |
| Keep | (no-op) leave the branch as-is |
| Discard | git checkout main && git branch -D <branch> |
| Verification check | Command |
|---|---|
| Dojo gate | bash scripts/verify.sh --check |
| Full tests | npm test / pytest / go test ./... / dotnet test |
| Clean tree | git status --porcelain |
| Full diff | git diff main --stat then git diff main |
| Commit log | git log main..HEAD --oneline |
Procedure
Step 1: Final Verification
Run via the powershell tool:
bash scripts/verify.sh --check
git status --porcelain
git log main..HEAD --oneline
git diff main --stat
All checks must pass. Anything failing → fix it, do not force-merge.
Step 2: Review the Full Diff
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.
- 12d ago First seen · 141 lines · 19 tokens per session scan A 6caf8b9c3e32
finishing-a-development-branch is a skill published in the GitHub repository andreaswasita/copilot-agents-dojo (53 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 1,104 once invoked, about $0.0001 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
shipping-a-pr
Use when finished work needs to ship as a pull request, or when the ask is about a PR — creating one, bringing it up to date, adding screenshots, watching its checks, or addressing its review comments. Not for reviewing a PR you are not shipping.
git-workflow
Use when naming or scoping a branch, writing or fixing a commit message, picking the gitmoji for a commit, untangling history (rebase versus merge versus squash), or cutting a versioned release — the portable git-convention layer for any repo. Covers gitmoji + Conventional Commits, SemVer tags, branch hygiene…
close
End session with verification, commits, and documentation.
gitlab-ops
Use this skill when performing VCS operations on GitLab or GitHub repositories — creating, updating, or closing issues and MRs, applying label taxonomy, running glab/gh CLI commands, or resolving project paths dynamically. Acts as the single source of truth for CLI command syntax and label conventions; consuming…
gitlab-portfolio
Use when you need a single-pane cross-repo health view across all vault-registered GitLab and GitHub projects. Discovers repos from overview.md frontmatter in /01-projects//, aggregates open issues, MRs, critical labels, and stale signals via parallel glab/gh calls, then writes an idempotent PORTFOLIO.md dashboard.…
npm-publish
Use when publishing this package to npm — a version release (npm publish), verifying the registry/pi.dev listing, or diagnosing npm auth failures (E403 2FA/token errors). Token-based flow via NPMTOKEN in .env.local with a temp userconfig, the leakage gate before every publish, post-publish verification and…