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/build-itemnpx skills add devstride/claude-plugin --skill build-itemgit 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 | $0.00077 | $0.08889 |
| Opus 5 | $0.00039 | $0.04444 |
| Sonnet 5 | $0.00015 | $0.01778 |
| Haiku 4.5 | $0.00008 | $0.00889 |
Grade A, and why
build-item 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 — 498 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.
Orchestrate ONE DevStride one-day leaf item (this org's Story or Defect types) end-to-end: select → In Progress → branch → build → review → PR → merge → completion ritual → sync → next. This is the ORCHESTRATOR. It composes the other delivery skills and owns ONLY the DevStride glue (selection, lane transitions, the completion ritual). Invoke them by name; do not re-spell what they do.
Argument — an item number, or next/empty for the next unblocked item. It may also SCOPE selection
to one plan by naming its ROOT (a parent item at any grouping level of the org's hierarchy,
e.g. this org's Module/Capability/Epic): next under I20100, or I20100
alone, meaning "the next unblocked item under this root" — a bare root is a SCOPE, never a story
to build, so resolve it as the plan root and then select within it. A specific item that is not
part of a sequenced plan is auto-detected as a one-off: $ARGUMENTS
Ground rules
- Full-auto through merge. Run the whole loop without pausing between steps. PAUSE only at a genuine fork: work gated on a human/infra decision that is the user's (AWS/DNS/SES/Stripe/ secrets/provisioning), an ambiguous or unverifiable review finding, or a destructive / outward-facing action. Record every deferral explicitly rather than silently skipping it.
- The DevStride MCP targets PRODUCTION. Lane moves and the completion ritual are real, user-visible changes to live items. The MCP cannot exercise branch code.
- Config:
.claude/ds-config.json— re-read it EVERY iteration; it wins over any literal here. - Skill freshness. The on-disk skills and config are the only source of truth, and they evolve
mid-initiative. Skill text you remember from an earlier iteration — especially through a
context compaction — is EXPIRED. Re-invoke each composed skill at the iteration that needs it
(the observed cost of not doing so:
references/progress-table.md). - The plan is a HYPOTHESIS. Validate the story's spec against the ACTUAL codebase before building — paths move, dependencies ship early, stated approaches turn out wrong. Correct the item's description rather than faithfully building the wrong thing, and keep it current as the work firms up, not only at the end. The item is the durable source of truth; the PR is not.
What ships with it
5 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 · 498 lines · 77 tokens per session scan A 7bd887205e83
build-item is a skill published in the GitHub repository devstride/claude-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 77 tokens to every session and 8,889 once invoked, about $0.0004 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…