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 makifbaysal/tasktrooper --skill incremental-commitsgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/incremental-commits)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/incremental-commits"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/incremental-commits/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/makifbaysal/tasktrooper/incremental-commits"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/incremental-commits.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 | $0.00031 | $0.00832 |
| Opus 5.5 | $0.00012 | $0.00333 |
| Sonnet 5.5 | $0.00006 | $0.00166 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
incremental-commits 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 8d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Incremental Commits
Overview
Work in bite-sized steps, not one large change. Small commits keep each step reversible and make revisions cheap to localize.
The Process
- Before coding, turn the task into a short ordered list of steps. Each step is ONE action worth 2–5 minutes:
- "Write the failing test" — a step
- "Run it and watch it fail" — a step
- "Write minimal code to pass" — a step
- "Run the tests, all green" — a step
- "Commit" — a step
- Commit locally after each green step on your task branch:
run_terminalwithgit add -A && git commit -m "<type>: <imperative summary>". Do not push, and do not callcommit_task_changesmid-run — the system commits and pushes your run's final state and opens the pull request at hand-off; a mid-run commit of your own is never the one that ships. - Each commit is one logical change: the test and the code that satisfies it belong together; unrelated changes never share a commit.
- Commit message: imperative summary line; explain WHY in the body when it is not obvious from the diff.
Rules of Thumb
- Never accumulate a large uncommitted change — if the diff is hard to describe in one sentence, you missed a commit point.
- A step should end with an independently verifiable state (test green, build passing).
- Setup/scaffolding folds into the step whose deliverable needs it; don't commit empty skeletons.
- If a step balloons mid-way, stop, commit what is green, and re-slice the rest.
Quick Reference
| Situation | Commit boundary |
|---|---|
| Test + code that satisfies it | One commit together |
| Two unrelated behaviors | Two commits |
| Refactor + behavior change | Separate commits (refactor first, while green) |
| Setup/scaffolding | Folded into the step that needs it — no empty-skeleton commits |
| Formatting-only change | Its own commit, never mixed with logic |
Worked Example
Task: add a priority field to task creation. A good branch history:
feat: add priority column migration
test: expect create to persist priority
feat: persist priority in create handler
test: default priority to "medium" when omitted
feat: default omitted priority to medium
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.
- 8d ago First seen · 68 lines · 31 tokens per session scan A a553ecedf113
incremental-commits is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 31 tokens to every session and 832 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 2026-10-05.
Other skills, from other repositories
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contextual-commit
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
git-workflow-management
Git workflow automation skill for commit message generation, branch management, pre-commit checks, and change history analysis.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.