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 agentmods add skills/2ykwang/cview/commit-fixupnpx skills add 2ykwang/cview --skill commit-fixupgit clone --depth 1 https://github.com/2ykwang/cviewWhat 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 | $0.00110 | $0.01354 |
| Opus 5 | $0.00055 | $0.00677 |
| Sonnet 5 | $0.00022 | $0.00271 |
| Haiku 4.5 | $0.00011 | $0.00135 |
Grade A, and why
commit-fixup 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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- commit-fixup — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commit-fixup
Absorb uncommitted changes into the existing commit each one should have been part of, leaving clean history. Four stages: safety checks → mapping → scope confirmation → execution and verification. This rewrites history, so don't skip any stage's checks.
1. Safety checks
git status --short # uncommitted changes
git merge-base HEAD origin/<default-branch> # establish base (use the repo's default branch)
git log --oneline <base>..HEAD # commits in scope
git branch -vv # upstream and push state
git log --merges --oneline <base>..HEAD # merge commits in range
git --version
Tell the user before proceeding if any of these hit:
- Branch already pushed → stop and ask. Rebasing means a force-push afterwards, and only the user makes that call. Never run a force-push on your own.
- Merge commits in range → stop. The rebase flattens the merge structure.
- git older than 2.44 → don't proceed. That version lacks the non-interactive
git rebase --autosquashthis skill relies on. Say the git version is too old to automate this safely and point at an upgrade (macOS:brew upgrade git, Ubuntu:apt upgrade git). - Untracked files are not absorption targets. Leave them alone.
2. Mapping: find the target commit for each changed file
For each modified file, find the commit in branch range that touched it last:
git log --oneline <base>..HEAD -- <file> | head -1
Why last-toucher: even when an earlier commit is the semantic owner, if a later commit also touched the file, fixing up into the earlier one makes the rebase conflict. The last-toucher rule guarantees a conflict-free, fully automatic rebase. It trades a little history aesthetics for safety — call out the affected files in the mapping table.
Mapping results fall into three buckets:
- Mapped: a commit in the branch touched that file
- Unmapped: no commit touched it (new file, or a change to a file from outside the branch)
- One file's changes needing to split across several commits → references/edge-cases.md
What ships with it
3 files 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.
- 2d ago First seen · 126 lines · 110 tokens per session scan A 118bca25ac80
commit-fixup is a skill published in the GitHub repository 2ykwang/cview (20 stars, last pushed 26d ago), licensed MIT. It adds 110 tokens to every session and 1,354 once invoked, about $0.0006 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
ship-it
Code commit, PR creation, merge, and issue closure workflow via GitHub CLI (gh). Triggers after a goal (GitHub Issue) implementation is complete — commit code, push branch, create PR, merge, then close the issue. Use when the user says "提交代码", "commit and merge", "创建PR", "合入", "关闭issue", "ship-it", or when a goal…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
submit-pr-from-current-changes
Create a branch, commit existing local changes, push them, and open a pull request. Use when submitting current work as a PR.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
prek
Use when setting up or running hooks with prek in any repository. prek is a Rust drop-in alternative to pre-commit for running Git hooks that check, format, lint, and validate code and repository files. Prefer it when speed, workspace mode, built-in hooks, shared toolchains, or native TOML configuration matter.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.