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 dryvist/claude-code-plugins --skill pr-stacksgit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWrote 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/dryvist/claude-code-plugins/pr-stacks)<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/pr-stacks"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/pr-stacks/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/dryvist/claude-code-plugins/pr-stacks"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/pr-stacks.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 | $0.00079 | $0.01110 |
| Opus 5.5 | $0.00032 | $0.00444 |
| Sonnet 5.5 | $0.00016 | $0.00222 |
| Haiku 4.5 | $0.00008 | $0.00111 |
Grade A, and why
pr-stacks 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 23d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Stacks
Stacked pull requests break one large change into an ordered chain of small, dependent PRs that are reviewed and merged independently — so you can keep building instead of waiting for each layer to merge.
feat/frontend → PR #3 (base: feat/api)
feat/api → PR #2 (base: feat/auth)
feat/auth → PR #1 (base: main) ← bottom
main / develop ← trunk
The bottom PR targets the trunk; each PR above targets the branch below it. GitHub evaluates branch protection, required checks, and CI against the trunk for every layer, not the PR's direct base — so a mid-stack PR is held to the same standard as the bottom one.
Trunk is the repository's default branch: main on a trunk repo, develop
on a git-flow repo (detect it per gh-cli-patterns — never assume). Promotion of
develop → main is unchanged: /promote-release.
[!IMPORTANT] All branches must live in the same repository — cross-fork stacks are not supported. The feature is in public preview, so a repository must opt in.
Provisioning — Nix, never gh extension install
gh and the gh stack extension are provisioned by the Nix configuration
(nix-home provides the source-built extension via programs.gh.extensions;
nix-ai carries the upstream agent skill). Never run
gh extension install github/gh-stack — ad-hoc tool installs are banned (see
nix-tool-policy). If gh stack is missing, the fix is a change in the Nix
repository, not an install command here.
Pre-GitHub workflow
Build bottom-up: foundational changes (types, schema, shared helpers) in the lowest layer; consumers and UI above. One focused, reviewable change per layer.
gh stack init # start a stack; trunk defaults to the default branch
gh stack add <branch-name> # add the next layer on top (or -Am "msg" to commit + add)
gh stack push # push the layers
gh stack submit # create the PRs; --open marks them ready (default: draft)
gh stack view # inspect layers, PR links, and status
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.
- 23d ago Changed 1d6833ab0a9a
- 1mo ago First seen · 90 lines · 79 tokens per session scan A 6d460f898bcb
pr-stacks is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 1,110 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 2026-09-13.
Other skills, from other repositories
nav-pilot
Dispatch a Navigator task doc to Pilot as a labeled GitHub issue. Use when user says "dispatch TASK-XX to Pilot", "hand off to Pilot", "send to Pilot", or "queue for Pilot". One-way handoff (Navigator authors the spec, Pilot executes autonomously).
meta-feedback
A feedback reporter that collects bug reports and feature requests, then formats them as GitHub Issues. GitHub Issues are shared records used by development teams to track work and problems.
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, review-based validation, and communication standards.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
auto-claude
Autonomous multi-agent coding with git worktree isolation, QA validation, and memory. Use for complex features requiring autonomous implementation.
github-ops
GitHub remote operations and README authoring: repo creation, metadata, releases, issue/PR management with preview-before-send, README as a landing page (badge row, features-as-benefits, screenshots, Recent Updates), and read-only security auditing. Triggers on: write a README, improve the README, README badges…