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 lugassawan/swe-workbench --skill principle-version-controlgit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/principle-version-control)<a href="https://agentmods.dev/skills/lugassawan/swe-workbench/principle-version-control"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/principle-version-control/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/lugassawan/swe-workbench/principle-version-control"><img src="https://agentmods.dev/badge/skills/lugassawan/swe-workbench/principle-version-control.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 | $0.00080 | $0.01307 |
| Opus 5.5 | $0.00032 | $0.00523 |
| Sonnet 5.5 | $0.00016 | $0.00261 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
principle-version-control 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 2mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Control & Collaboration
git log is a debugging instrument. Its quality depends entirely on the discipline of the people who wrote to it.
Atomic commits — one logical change
One commit, one reason to revert it. The test: can you describe the change in a short subject line without using "and"?
- Atomic commits make
git bisecteffective — a failing test traces to the exact change that introduced it. - Atomic commits make reverts safe — reverting "add feature X" does not also undo "fix unrelated bug Y".
- Split a large change by concern: refactor first (pure mechanical moves), then behavior change, then test additions.
Commit messages — what makes them load-bearing
Subject line: imperative mood, ≤50 characters, no trailing period. Body: wrap at 72 characters, explain why, not what.
[type] Short imperative subject (≤50 chars)
Why this change was made. What would break if reverted.
Link the issue or ticket. Note non-obvious constraints.
Format schemes — Conventional Commits (feat:, fix:), [type] Subject, JIRA-prefix — are all valid conventions. Pick one; apply consistently and enforce via a commit-msg hook. Example: the swe-workbench plugin repo enforces [type] Subject via .githooks/commit-msg. Before authoring commit messages, detect the host repo's convention via the detection step in swe-workbench:workflow-commit-and-pr.
Never mix formatting and logic
Formatting commits (whitespace, import sort, rename) belong in a separate commit from behavior changes. Reviewers can skim a formatting-only commit in seconds; mixing it into a logic commit makes the diff unreadable and breaks git blame for every touched line.
Branching — feature-branch vs trunk-based
Feature branches work when: CI is slower than a few minutes, teams have >2 engineers, or releases are discrete.
- Keep branches short-lived (days, not weeks). Long-lived branches accumulate merge debt.
- Branch naming convention keeps the log readable —
feat/<issue>-<slug>,fix/<slug>,chore/<slug>.
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.
- 2mo ago First seen · 93 lines · 80 tokens per session scan A bb9b1cfe118b
principle-version-control is a skill published in the GitHub repository lugassawan/swe-workbench (3 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 1,307 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.
principle-version-control compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| principle-version-controllugassawan/swe-workbench | Skill | 3 | 3d ago | MIT | A | 80 | Claude Code |
| releasehyhmrright/brooks-lint | Skill | 1.6k | today | MIT | A | 135 | Claude Code, Codex |
| unslop-commitMohamedAbdallah-14/unslop | Skill | 179 | 5d ago | MIT | A | 139 | Claude Code |
| releasegtapps/hermitd | Skill | 84 | today | MIT | A | 104 | Claude Code, Codex |
| evolve-lite:unpublishAgentToolkit/altk-evolve | Skill | 136 | yesterday | Apache-2.0 | A | 23 | Claude Code, Codex |
| commitgtapps/hermitd | Skill | 84 | today | MIT | A | 90 | Claude Code, Codex |
| commitnitinjain999/platform-skills | Skill | 71 | 2d ago | Apache-2.0 | A | 74 | Claude Code |