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/ably/ably-cli/ably-reviewnpx skills add ably/ably-cli --skill ably-reviewgit clone --depth 1 https://github.com/ably/ably-cliWhat 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 | $0.00101 | $0.03688 |
| Opus 5 | $0.00051 | $0.01844 |
| Sonnet 5 | $0.00020 | $0.00738 |
| Haiku 4.5 | $0.00010 | $0.00369 |
Grade A, and why
ably-review 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 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.
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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ably Branch Review
This skill reviews only the changes on the current branch (compared to main) against the conventions defined in the ably-new-command skill. It uses a combination of LSP for structural analysis (type hierarchies, call chains) and grep/read for text-pattern checks, choosing the right tool for each check.
Unlike ably-codebase-review which sweeps the entire codebase, this skill is scoped to what has changed on the current branch, making it fast and focused for pre-PR review.
Tool selection guide
Use LSP when you need type-system awareness:
goToDefinition— resolve what base class a command actually extendsfindReferences— trace all callers of a method through inheritancehover— reveal resolved types, inherited members, full type hierarchydocumentSymbol— list all methods/properties in a class structurally
Use grep/read when a text match is sufficient:
this.error()calls in command files- Component string casing in
this.fail()andlogCliEvent()calls new Error(...)wrapping inthis.fail()calls (unnecessary — accepts strings)shouldOutputJsonguards aroundthis.log()formatSuccess()calls ending with.formatProgress()calls with manual...chalk.cyan()whereformatResource()should be used- Quoted resource names instead of
formatResource(name) --json/--pretty-jsoninstatic examplesarrays- Flag spreads like
...productApiFlags,...durationFlag,...clientIdFlag waitUntilInterruptedOrTimeoutusage- Missing test files (glob for them)
--durationflag in subscribe test files- Mock helper imports (
getMockAblyRealtime,getMockAblyRest,getMockConfigManager)
Step 0: Verify LSP prerequisites
Before doing any analysis, check that the LSP tooling is available:
- Check for the LSP tool — verify the
LSPtool is available in your tool list. If it is not, tell the user:The LSP plugin is not installed. Install it by running:
claude plugin add anthropic/claude-code-lspThen restart Claude Code and re-run this skill. Stop here — do not proceed without the LSP tool.
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 · 195 lines · 101 tokens per session scan A b8053cf98411
ably-review is a skill published in the GitHub repository ably/ably-cli (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 101 tokens to every session and 3,688 once invoked, about $0.0005 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…