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 mhawthorne/gza --skill gza-rebasegit clone --depth 1 https://github.com/mhawthorne/gzaWrote 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/mhawthorne/gza/gza-rebase)<a href="https://agentmods.dev/skills/mhawthorne/gza/gza-rebase"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-rebase/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/mhawthorne/gza/gza-rebase"><img src="https://agentmods.dev/badge/skills/mhawthorne/gza/gza-rebase.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 114 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 | $0.00032 | $0.02072 |
| Opus 5 | $0.00016 | $0.01036 |
| Sonnet 5 | $0.00006 | $0.00414 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade A, and why
gza-rebase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rebase onto Target Branch
Rebase the current branch onto a local target branch, resolving any merge conflicts interactively.
Process
Treat the current worktree root as fixed. Set:
GZA_WORKTREE_ROOT="${GZA_WORKTREE_ROOT:-/workspace}"
When not running in Docker and /workspace is not the current checkout, set GZA_WORKTREE_ROOT to the existing checkout root before running any Git command. Run every Git command as git -C "$GZA_WORKTREE_ROOT" ...; do not rely on the shell's current directory.
Modes
- Default mode: run the full flow (Steps 1-7).
--continuemode: assume a rebase conflict is already in progress, skip Steps 1-3, and start directly at Step 4.- In this mode, do not check for a clean working tree; the tree is expected to be dirty because of conflict markers.
- If no rebase is in progress, stop and report that
git rebase --continuecannot proceed.
--automode: unattended rebase for background workers. Same as default mode but:- Do NOT use AskUserQuestion — resolve all conflicts autonomously using best judgment.
- If a conflict is truly ambiguous and cannot be resolved confidently, abort the rebase and report failure.
- Treat edit-vs-delete and two-sided-modification conflicts as ambiguous unless you can preserve every still-referenced symbol with high confidence. Do not silently prefer deletion.
- Uncommitted changes may be present in the working tree (e.g. leftover from an interrupted run). Stash them before rebasing and restore with
git -C "$GZA_WORKTREE_ROOT" stash popafterwards. - Do NOT use remote git operations. Do not run
git fetch,git ls-remote, HTTPS fallback fetches, or modify git remotes/config. Use only local refs already present in the repo. If the required local target is missing, stop and report failure. - If worktree metadata is missing, detached in an unexpected way, points outside
GZA_WORKTREE_ROOT, or cannot prove the checkout root, abort and report the invalid state. Do not reconstruct branch linkage.
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.
- 5d ago Changed · -1 lines f9301495c5c9
- 6d ago Changed · +5 lines 7b339f1effd5
- 11d ago First seen · 120 lines · 32 tokens per session scan A 47b9995735eb
gza-rebase is a skill published in the GitHub repository mhawthorne/gza (12 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,072 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 2026-08-30.
Other skills, from other repositories
flow-next-land
Autonomous PR babysitter tick. Fixes CI, resolves feedback, merges when converged, closes the spec, releases. Emits LANDVERDICT. Use when asked to land PRs.
flow-next-worktree-kit
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
share-a-library
Use when a managed library is ready to publish to GitHub and hand to teammates as an install command. Run the GitHub publishing steps, then return the exact shareable install command.
development-workflow
Detailed development workflow with modular patterns for git, review, testing, and deployment.
ship-it
A GitHub workflow for finishing an implemented issue: commit the relevant changes, push a branch, create a pull request, merge it, and close the issue. GitHub is a service for hosting code and reviewing changes, and a pull request is a proposed change for review.
fix-pr-review-loop
Use when the user asks to fix a PR review and drive it to approval autonomously — "fix the PR review and loop until approved", "fix-pr-review-loop", "keep addressing review comments until this PR is approved". Takes an optional PR number/URL (defaults to the current branch's PR). Repeatedly calls fix-pr-review, waits…