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/muthuspark/solid-audit/lspnpx skills add muthuspark/solid-audit --skill lspgit clone --depth 1 https://github.com/muthuspark/solid-auditWhat 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 | $0.00017 | $0.01823 |
| Opus 5 | $0.00009 | $0.00911 |
| Sonnet 5 | $0.00003 | $0.00365 |
| Haiku 4.5 | $0.00002 | $0.00182 |
Grade A, and why
lsp 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
This skill activates when the user runs /lsp (optionally with a file path argument, e.g. /lsp src/models/shapes.py).
Scope Detection
Determine which files to analyze using this priority order:
- Argument — If the user provided a file or directory path after
/lsp, use that directly. - Git staged — Run
git diff --cached --name-only. If output is non-empty, use those files. - Git unstaged — Run
git diff --name-only. If output is non-empty, use those files. - Ask user — If no git diff is available, ask for a file or directory path.
Always skip: *.lock, package-lock.json, yarn.lock, pnpm-lock.yaml, Gemfile.lock, composer.lock, **/migrations/**, **/__generated__/**, **/fixtures/**, **/*.min.js
LSP Fix Logic
Detection
A subclass violates LSP when it cannot be used in place of its base class. Look for:
-
NotImplementedError / not implemented throws:
- Python:
raise NotImplementedErrorin a method inherited from the base class - TypeScript/Java:
throw new Error("not implemented")orthrow new UnsupportedOperationException()in an overriding method - C#:
throw new NotImplementedException()in an overriding method - Kotlin:
throw UnsupportedOperationException()orTODO()used as a stub in an overriding method - Ruby:
raise NotImplementedErrorin an overriding method - PHP:
throw new \BadMethodCallException("not implemented")in an overriding method
- Python:
-
Narrowed preconditions: A subclass method rejects inputs the base class accepts (e.g., base accepts
int, subclass only acceptsint > 0) -
Strengthened postconditions: A subclass method returns a more restricted type or raises exceptions not declared in the base class contract
-
Silent no-ops: A subclass overrides a method with an empty body (
passor{}) that the base class defines as meaningful behavior
Fix Strategy
Option 1 — Flatten the hierarchy:
If the subclass doesn't truly extend the base (e.g., Penguin doesn't fly like Bird), remove the inheritance and make each class independent.
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 · 208 lines · 17 tokens per session scan A 35e245470872
lsp is a skill published in the GitHub repository muthuspark/solid-audit (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 1,823 once invoked, about $0.0001 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…