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/jnPiyush/AgentXnpx agentmods add skills/jnpiyush/agentx/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/jnpiyush/agentx/finishing-a-development-branch)<a href="https://agentmods.dev/skills/jnpiyush/agentx/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/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/jnpiyush/agentx/finishing-a-development-branch"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/finishing-a-development-branch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Tool Misuse · line 102 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00073 | $0.02186 |
| Opus 5.5 | $0.00029 | $0.00874 |
| Sonnet 5.5 | $0.00015 | $0.00437 |
| Haiku 4.5 | $0.00007 | $0.00219 |
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 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finishing A Development Branch
WHEN: The work on a feature, bug-fix, spike, or experiment branch is functionally complete and the agent is about to choose between merge, open PR, keep open for follow-up, or discard. This is the moment where unfinished cleanup turns into branch-graveyard debt.
When to Use This Skill
Load this skill when:
- Tests pass on the branch and the agent is about to claim "done"
- The Engineer or Auto-Fix Reviewer is about to commit and push but has not chosen a disposition
- An experimentation-loop attempt finished (kept or reverted) and the working branch still exists
- A worktree exists for the branch and the agent is about to switch away without removing it
- A long-running spike branch has been superseded by a different approach
Skip when:
- The branch is the long-lived
main/master/develop-- this skill is about feature branches - The user explicitly wants to keep the branch open without choosing a disposition (rare; ask)
Prerequisites
- Branch contains a coherent change set with a clear claim of completion
- Quality loop status known (
.frontier/runtime/frontier.ps1 loop status) - Test results for the current HEAD are known and recorded
- Knowledge of whether the work has an issue and what its current status is
Rationalization Table
Why agents leave branches half-finished.
| Rationalization | Reality |
|---|---|
| "I will clean it up later." | Later never comes. Stale branches accumulate, merge conflicts compound, and reviewers can no longer tell which branch is current. Dispose now. |
| "The tests pass, the work is done." | Tests passing is necessary, not sufficient. Done means: loop complete, compound capture resolved, branch disposition chosen, cleanup executed. |
| "I will leave the worktree around in case I need it." | Worktrees you do not need rot. Either remove the worktree or commit to using it again within the next session. |
| "I will merge straight to master to avoid PR overhead." | Direct merge skips the review gate, the CI gate, and the audit trail. Only legal for trivial docs / config in solo Local Mode. |
| "I will open a draft PR and come back to it." | A draft PR with no description and no reviewer assigned is a parking lot, not a workflow. Either it is ready for review, or close it and re-open later. |
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 Changed 1cff0f70796a
- 20d ago Changed 484344346d9b
- 1mo ago Changed 21f3c60701c9
- 1mo ago First seen · 187 lines · 73 tokens per session scan A 19d528ce87ae
finishing-a-development-branch is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 73 tokens to every session and 2,186 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…