Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add technicalpickles/pickled-claude-plugins/plugin install actually-lspWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/actually-lsp-doctor)<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/actually-lsp-doctor"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/actually-lsp-doctor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/actually-lsp-doctor"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/actually-lsp-doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00102 | $0.01527 |
| Opus 5 | $0.00051 | $0.00763 |
| Sonnet 5 | $0.00020 | $0.00305 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
actually-lsp-doctor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/actually-lsp-doctor
Parse the user's args from the invocation:
fixas the first arg means skip the diagnostic report and jump straight to action.rust|typescript|rubyas an arg narrows focus to that ecosystem.- No args: full diagnostic report followed by interactive fix.
Step 1: Read project state
Read .claude/actually-lsp.json in the current project root. If missing, run detection: source lib/detect.sh and lib/ecosystems.sh from the plugin root (the env var CLAUDE_PLUGIN_ROOT points there), call detect_ecosystems "$PWD", and for each detected ecosystem compute the current state per the rules in CONTEXT.md.
Step 2: Diagnose (unless fix arg present)
Output a per-ecosystem report. For each ecosystem:
- State (from
CONTEXT.md's six states) - For non-
readyecosystems: what's needed to reachready - For
dismissedecosystems: note them but don't propose action
Keep tone terse. No celebration messaging.
Step 3: Act
For each ecosystem in no-lsp-plugin, server-not-runnable, or error:
no-lsp-plugin: try claude plugin install <recommended_plugin>@claude-plugins-official via Bash. The user gets a permission prompt. If denied, output the slash command form (/plugin install <recommended_plugin>@claude-plugins-official) and ask the user to run it themselves.
server-not-runnable: run env fixes per ecosystem via Bash. All env fixes auto-run; the user has implicit project consent. Check readiness_source in the state file to aim the fix: binary means the server binary is missing or non-functional (fix the binary, not the deps); heuristic/probe means the binary ran but the project env needs work (build deps).
- TypeScript:
npm install. - Ruby:
bundle install, plusgem install ruby-lspifcommand -v ruby-lspis empty. - Rust: the binary is the usual culprit, and
cargo builddoes NOT fix it. Therust-analyzer-lspplugin launches a barerust-analyzerfrom PATH, which is often a rustup proxy that is non-functional when therust-analyzercomponent isn't installed for the active toolchain (rust-analyzer is unavailable for the active toolchain). Recover in order:- Binary: if
rust-analyzer --versionfails or printsunavailable for the active toolchain(test it, don't trustcommand -valone, since the proxy resolves but doesn't run), runrustup component add rust-analyzer. This makes the barerust-analyzerthe LSP tool launches actually work. Ifrustupis absent, tell the user to install rust-analyzer so a working binary is first on PATH (rustup component, mise, or brew) and stop. - Standard library: rust-analyzer needs
rust-srcto load std; without it nav can return nothing. Ifrustc --print sysroothas nolib/rustlib/src, runrustup component add rust-src. - Deps / proc-macros:
cargo buildso dependency and macro-generated symbols resolve (intra-project nav works without this, but full semantics need it). Then let Step 5 re-probe to confirm the server actually answers.
- Binary: if
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.
- 9d ago First seen · 81 lines · 102 tokens per session scan A 25ba7a1aaf5b
actually-lsp-doctor is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (10 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 1,527 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
absolute-debt
Lint and typecheck debt paydown: clear pre-existing repo-wide lint/type violations and suppressions (@ts-ignore, # type: ignore) one rule per wave, fixing causes not symptoms. Runs on green main. For diff-scoped quality use absolute-simplify. Triggers on "absolute debt", "fix our lint warnings", "clear the type…
absolute-deflake
Flaky test fixes: detect nondeterministic tests empirically (repeat/shuffle/parallel runs), diagnose the root cause, fix it — never retry/skip/sleep — and verify across many randomized runs. Triggers on "absolute deflake", "fix flaky tests", "CI is flaky", "this test fails randomly/intermittently".
absolute-prune
Dead code and dependency cleanup, repo-wide: unused deps, unreferenced exports, unreachable code, orphaned files — removed only with tool evidence, in reversible waves. Runs on green main. For diff-scoped cleanup use absolute-simplify. Triggers on "absolute prune", "remove dead code", "find unused deps/exports", "what…
scientific-debugging
A method for debugging software by observing the problem, forming possible explanations, running small experiments, and then fixing and checking the result.
bug-fix
A structured process for fixing software bugs, including reproducing the problem, finding its root cause, and writing a test that prevents it from returning. A regression test is an automated check that catches a previously fixed problem.
debugging
A systematic method for finding the underlying cause of a software bug by observing the failure, forming a hypothesis, and testing it.