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 tolgakisaogullari/SumelaOS --skill finishing-a-development-branchgit clone --depth 1 https://github.com/tolgakisaogullari/SumelaOSWrote 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/tolgakisaogullari/sumelaos/finishing-a-development-branch)<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/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/tolgakisaogullari/sumelaos/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/finishing-a-development-branch.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 | $0.00034 | $0.02309 |
| Opus 5 | $0.00017 | $0.01154 |
| Sonnet 5 | $0.00007 | $0.00462 |
| Haiku 4.5 | $0.00003 | $0.00231 |
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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<execution_workflow> Execute these steps strictly in sequence. DO NOT announce the skill.
-
PRE-FLIGHT TEST & SECURITY CHECK (ADAPTIVE):
- Run the project's test suite (e.g.,
npm test,pytest,cargo test) to ensure NO existing tests are broken (Regression Check). - If TDD Mode was Enabled: Verify all newly written tests pass.
- If TDD Mode was Skipped: Verify that the project successfully builds/compiles, AND ensure any required security tests (from
secure-coding-standard) pass successfully. - If ANY required test or build FAILS: Show failures to the user and STOP. Do not proceed to Step 2.
- If tests/build PASS: Proceed to Step 2.
- Run the project's test suite (e.g.,
-
MANDATORY COMMIT (THE CHECKPOINT):
- Run
git statusto check for uncommitted/staged changes. - CRITICAL REVIEW GATE: You MUST ensure that the
requesting-code-reviewskill was executed and explicitly approved before proceeding. "Inline execution", "I applied secure coding standards myself", or "Tests passed" are NOT valid excuses. If therequesting-code-reviewskill was NOT formally executed, you MUST STOP this workflow immediately and runrequesting-code-review. Do not commit until the review is fully resolved. - CRITICAL REMINDER: If this skill was invoked AFTER review feedback was already received and applied inline, still verify that
requesting-code-reviewwas formally dispatched earlier in the session. Inline review execution (subagent dispatched directly without going through therequesting-code-reviewworkflow) does NOT satisfy the review gate. If formal review was skipped, STOP and runrequesting-code-reviewbefore proceeding. - Commit the approved STAGED changes using a descriptive, conventional commit message (e.g.,
git commit -m "feat: implement [feature] based on plan"). If critical security mitigations were applied, mention them briefly in the commit body. - NEVER merge or push without committing the approved work first.
- Run
-
DETERMINE BASE:
- Identify base branch silently (
git merge-base HEAD mainorgit merge-base HEAD master).
- Identify base branch silently (
-
PRESENT OPTIONS:
- PRE-FLIGHT: Before presenting options, check if the current feature branch is already merged into base (e.g., via fast-forward performed outside this skill). Run
git merge-base --is-ancestor <current-feature-branch> <base-branch>silently. If it returns true (0), the branch is already merged. In this case, SKIP Options 1-4 selection and proceed directly to Step 7 (Memory Persistence). Do NOT ask the user to choose; the merge is already a fact. Present EXACTLY these 4 options to the user. Do not add any explanations or conversational filler: "Implementation, tests, and security reviews complete. Changes are committed. What would you like to do?
- Merge back to locally AND update Second Brain
- Push, create a Pull Request AND update Second Brain
- Keep the branch as-is (I'll handle it later)
- Discard this work" Wait for user selection.
- PRE-FLIGHT: Before presenting options, check if the current feature branch is already merged into base (e.g., via fast-forward performed outside this skill). Run
-
EXECUTE CHOICE:
- Dirty worktree guard (before Options 1, 2, or 4): run
git status --short. If unrelated dirty files are present, STOP and ask the user whether to stash them. If stashing is approved, use a descriptive stash name and later report: stash name/message, captured files, why it was needed, and whether it was reapplied or dropped. - Option 1 (Merge):
git checkout <base>,git pull,git merge <current-feature-branch>, run tests again on merged result. If pass,git branch -d <current-feature-branch>. Proceed to Step 6. - Option 2 (PR): Push branch (
git push -u origin <branch>). Create PR using the GitHub connector/IDE tool when available, orgh pr createotherwise. The PR body MUST include Summary, Security Notes, and Test Plan sections. Bash-compatible fallback:
PowerShell-compatible fallback: create the same body in a temporary markdown file, then rungh pr create --title "<conventional-prefix>: <feature summary>" --body "$(cat <<'EOF' ## Summary - <2-3 bullets describing what changed and why> ## Security Notes - <list any secure-coding-standard mitigations applied; write "None applicable." if not relevant> ## Test Plan - [ ] <verification steps the reviewer should run> EOF )"gh pr create --title "<conventional-prefix>: <feature summary>" --body-file <temp-file>. Do NOT cleanup worktree. - Option 3 (Keep): Do nothing. Report "Worktree preserved." Do NOT cleanup worktree.
- Option 4 (Discard): Show the user this exact warning before deleting anything:
Require them to type EXACTLY "discard" to confirm. Any other input aborts. If confirmed: checkout base,This will permanently delete: - Branch: <branch-name> - Commits: <list of commit hashes + first lines> - Worktree at: <worktree-path> Type 'discard' to confirm.git branch -D <current-feature-branch>. Proceed to Step 6.
- Dirty worktree guard (before Options 1, 2, or 4): run
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 · 98 lines · 34 tokens per session scan A 8e7b133ef483
finishing-a-development-branch is a skill published in the GitHub repository tolgakisaogullari/SumelaOS (4 stars, last pushed 18d ago), licensed MIT. It adds 34 tokens to every session and 2,309 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…