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 DJRHails/dotfiles --skill patch-stack-actiongit clone --depth 1 https://github.com/DJRHails/dotfilesWrote 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/djrhails/dotfiles/patch-stack-action)<a href="https://agentmods.dev/skills/djrhails/dotfiles/patch-stack-action"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/patch-stack-action/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/djrhails/dotfiles/patch-stack-action"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/patch-stack-action.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 | $0.00046 | $0.02599 |
| Opus 5.5 | $0.00018 | $0.01040 |
| Sonnet 5.5 | $0.00009 | $0.00520 |
| Haiku 4.5 | $0.00005 | $0.00260 |
Grade A, and why
patch-stack-action 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 1mo 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Patch Stack
Manage patch-stack forks powered by DJRHails/patch-stack-action.
When to use
- The repo references
DJRHails/patch-stack-actionin a workflow - Commits on
mainare prefixed withpatch-stack: - The repo has
patch/*branches - The user wants to set up a new patch-stack fork
Concepts
A patch-stack fork maintains a clean separation between upstream code and your changes:
| Branch | What it is |
|---|---|
base (or configured name) |
Read-only mirror of upstream main. Updated automatically by the nightly sync. Never commit to this directly. |
patch/* |
One branch per logical change. Each is rebased onto base automatically. This is where you do your work. |
main |
The integration branch. Built automatically: base + all patches squash-merged (prefixed patch-stack:). Never commit to this directly except fork: prefixed commits for fork-specific infra. |
Key rule: main is rebuilt from scratch on every sync. Only fork: prefixed commits and patch-stack: squash-merges survive. All real work happens on patch/* branches.
Day-to-day patch editing workflow
Creating a new patch
Every patch needs three things: a patch/* branch from base, a push, and a local PR targeting base.
# 1. Always branch from base, not main
git checkout -b patch/my-feature origin/base
# 2. Make your changes, commit
git add <files>
git commit -m "feat(scope): description"
# 3. Push
git push origin patch/my-feature
# 4. ALWAYS create a PR targeting base (not main)
gh pr create --head patch/my-feature --base base
The PR against base is required. The sync action uses it to track patch state, generate squash commit messages on main, and link to upstream PRs. Without it the patch is invisible to the workflow.
Editing an existing patch
# Check out the patch branch
git checkout patch/my-feature
# Or use a worktree to avoid leaving main
git worktree add .data/worktrees/my-feature patch/my-feature
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.
- 1mo ago First seen · 303 lines · 46 tokens per session scan A 720500ea26c6
patch-stack-action is a skill published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 2,599 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
autopilot
Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).
autopilot-triage
Vet open issues for autonomous resolution and queue the qualifying ones with the autopilot-queued label — the start-of-day "fill the queue" half of the triage → run split.
create-pr
Create a pull request with auto-generated description, issue linking, ROADMAP updates, and PR-metadata validation.
merge-pr
Merge a pull request with status checks, squash merge, and branch cleanup. Handles worktree contexts.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
typesafe-ai
Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives. Its System One models, including Jev, turn natural language and application state into typed judgments and probabilities that code can combine. Use when a feature needs programmable common sense, when…