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/devstride/claude-plugin/prnpx skills add devstride/claude-plugin --skill prgit clone --depth 1 https://github.com/devstride/claude-pluginWhat 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 | $0.00031 | $0.03130 |
| Opus 5 | $0.00015 | $0.01565 |
| Sonnet 5 | $0.00006 | $0.00626 |
| Haiku 4.5 | $0.00003 | $0.00313 |
Grade A, and why
pr 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 yesterday.
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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human output. Read ${CLAUDE_PLUGIN_ROOT}/skills/build-item/references/plain-language-output.md once per top-level run; composed skills reuse it. Apply it to every message.
Open a PR for the current branch and run it through review + CI gating by composing
review, then optionally link it to its DevStride item. This skill owns PR creation
and linking only — invoke the engine, don't re-spell it.
Optional argument (DevStride item number): $ARGUMENTS
Config: .claude/ds-config.json (baseBranch, integrationBranch, hotfixBaseBranch,
review.*), authoritative over any literal here.
Delivery profile. Driven by build-item, take the profile the caller resolved. Standalone —
or whenever no caller supplied one — resolve it by the resolution order in
${CLAUDE_PLUGIN_ROOT}/skills/plan/references/delivery-profiles.md (the canonical contract — cite
it, never restate it), apply the repo's profileOverrides as it specifies, and announce it with
its source. Two profile values reach this flow: releaseCiOrdering carries the profile FLOOR
that expensive CI runs once, on the final reviewed and pre-ship-checked HEAD; and
reviewerRegistrationWindowMinutes bounds registration proof inside review. Neither may make
PR entry wait: this skill captures each request's baseline and hands off immediately (step 1).
Pass the resolved profile to review (step 2).
Working base. For a feature PR: the branch the CALLER passed (build-item derives the
story's epic integration branch), else integrationBranch if non-null, else baseBranch.
Hotfix PRs target hotfixBaseBranch regardless. Read "the working base" wherever a step says
develop.
Two shapes that are NOT this flow
- PRODUCTION RELEASE. Base ==
release.productionBranchand head ==release.releaseSource(release.releaseSource→release.productionBranch) is the production cut that triggers the repo's configured deploy, and it carries the documentation hooks and an owner-gated merge. Detect it and invoke/devstride:releaseinstead. Ahotfix → masterPR is different — a single fix, not a promotion — and stays in this flow. - EPIC RELEASE PR (caller says so;
build-itemstep 8). Head = the epic integration branch, base =baseBranch. The body's FIRST configured section (fallback## Simple Description) leads with the EPIC (number, title, what a consumer can now do) and lists the constituent stories ([N] I##### — title); the rest describes the epic-level delta. No story-level slow-gate exemption. Do NOT--delete-branch— the caller owns that cleanup, and performs it only whenepicIntegrationBranches.deleteBranchAfterReleaseis true.
Autonomous (driven-by-build-item) mode. Take the pre-supplied base as given (do not
re-ask step 0); tell review it is driven; SKIP step 3 — that loop owns linking, and
doing it here too double-owns it. Still pause only at a genuine fork.
What ships with it
2 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.
- yesterday First seen · 194 lines · 31 tokens per session scan A e869db7ef8d1
pr is a skill published in the GitHub repository devstride/claude-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 3,130 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…