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/restarter/lets-workflow/loop-bb-prnpx skills add restarter/lets-workflow --skill loop-bb-prgit clone --depth 1 https://github.com/restarter/lets-workflowWhat 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 | $0.00118 | $0.02004 |
| Opus 5 | $0.00059 | $0.01002 |
| Sonnet 5 | $0.00024 | $0.00401 |
| Haiku 4.5 | $0.00012 | $0.00200 |
Grade A, and why
loop-bb-pr scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
│ (curl fallback planned for v1.1.) │ How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
loop-bb-pr
Compose a /loop that periodically polls a Bitbucket PR via the bb-api wrapper and surfaces changes (new comments, review state, merge, decline).
The skill never invokes /loop itself at initial start — Claude Code's /loop is a UI command. It composes the prompt and presents for paste; once active, the autonomous run uses ScheduleWakeup directly per tick (that part is model-callable).
IMPORTANT: If the spec below invokes any deferred tool (e.g.
AskUserQuestion), you MUST load and call it as specified.
Step 1: Resolve PR URL
Parse args parameter for URL. If not provided, AskUserQuestion:
AskUserQuestion(
questions=[{
question: "Bitbucket PR URL to watch?",
header: "PR URL",
options: [
{ label: "I'll paste it", description: "Send the bitbucket.org/.../pull-requests/N URL in your next message" },
{ label: "Cancel", description: "Abort composition" }
],
multiSelect: false
}]
)
If user picks "I'll paste it", wait for URL in their next message.
Normalize then validate — real BB URLs often have query strings (?at=branch&type=...) or trailing slashes. Strip before regex match:
URL="<from input>"
URL="${URL%%\?*}" # strip query string (everything from ? onward)
URL="${URL%#*}" # strip fragment (everything from # onward)
URL="${URL%/}" # strip trailing slash
Then strict validation — normalized URL must match exactly:
^https://bitbucket\.org/[a-zA-Z0-9_-]+/[a-zA-Z0-9_.-]+/pull-requests/[0-9]+$
If validation fails: surface error, exit. Do NOT proceed with malformed URL — the composed prompt may persist (if user switches to interval mode in v1.1) and we don't want arbitrary input in .claude/scheduled_tasks.json.
Extract via regex or sed (from normalized URL):
WORKSPACE— first segment afterbitbucket.org/REPO— second segmentPR_ID— final numeric segment
Step 2: Verify bb-api availability
which bb-api 2>/dev/null
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.
- 2d ago First seen · 173 lines · 118 tokens per session scan A 2791feb6f896
loop-bb-pr is a skill published in the GitHub repository restarter/lets-workflow (17 stars, last pushed 9d ago), licensed MIT. It adds 118 tokens to every session and 2,004 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…