Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/QBall-Inc/the-bulwarknpx agentmods add skills/qball-inc/the-bulwark/setup-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/qball-inc/the-bulwark/setup-lsp)<a href="https://agentmods.dev/skills/qball-inc/the-bulwark/setup-lsp"><img src="https://agentmods.dev/badge/skills/qball-inc/the-bulwark/setup-lsp/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/qball-inc/the-bulwark/setup-lsp"><img src="https://agentmods.dev/badge/skills/qball-inc/the-bulwark/setup-lsp.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 | $0.00036 | $0.02936 |
| Opus 5 | $0.00018 | $0.01468 |
| Sonnet 5 | $0.00007 | $0.00587 |
| Haiku 4.5 | $0.00004 | $0.00294 |
Grade B, and why
setup-lsp scanned grade B 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- [ ] **Stage 4 — Settings**: `ENABLE_LSP_TOOL=1` set in `~/.claude/settings.json` and shell profile Copies of this mod
1 near-identical copy found in the catalogue:
- setup-lsp — 95% identical, 632 lines differ
How it starts
The opening of the file, as written. The whole thing — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup LSP
Configure Language Server Protocol integration for Claude Code projects. LSP replaces text-based grep/glob searches with semantic code intelligence: go-to-definition, find-references, hover type info, call hierarchy, and real-time error detection.
Mandatory Execution Checklist (BINDING)
Every applicable item below is mandatory. No deviations. No substitutions. No skipping.
This skill uses a 9-stage pipeline. You are the orchestrator. Follow every item in order. Do NOT return to the user until all applicable items are checked.
- Stage 1 — Parse: Arguments read, MODE determined (
full|verify|troubleshoot),--langextracted if present - Stage 2 — Detect:
references/server-registry.mdloaded, manifest files scanned, DETECTED_LANGUAGES presented to user - Stage 3 — Binaries: Binary install command run for each confirmed language
- Stage 4 — Settings:
ENABLE_LSP_TOOL=1set in~/.claude/settings.jsonand shell profile - Stage 5 — Guide Plugin Install: Present user with exact plugin names and instructions to install via
/pluginor CLI - Stage 6 — Checkpoint: Session ID captured via
${CLAUDE_SESSION_ID}, exactclaude --resumecommand presented to user, execution STOPPED - Stage 7 — Verify: (on
--verify) Debug log read,Total LSP servers loaded: Nchecked - Stage 8 — Diagnostics: (if verification failed or
--troubleshoot)references/troubleshooting.mdloaded, issues checked in order - Stage 9 — Report:
templates/diagnostic-output.yamlloaded, diagnostic YAML written tologs/diagnostics/, summary presented to user
Do NOT declare complete until all applicable checkboxes are marked.
When to Use This Skill
| Trigger Pattern | Scenario | Mode |
|---|---|---|
| Starting LSP setup from scratch | Project has no LSP configured | Full setup (no flags) |
| After restarting Claude Code following plugin install | Session resumed, verifying LSP loaded | --verify |
| LSP tools not appearing or servers not responding | Debugging a broken LSP configuration | --troubleshoot |
What ships with it
3 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.
- 9d ago First seen · 321 lines · 36 tokens per session scan B 1399aece2ebf
setup-lsp is a skill published in the GitHub repository QBall-Inc/the-bulwark (8 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 2,936 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
privacy-guard
Prevents private infrastructure details (node hostnames, internal project names, local usernames and personal emails, absolute home paths, private and VPN IP ranges) from leaking into public repositories through commits, PRs, docs or release artifacts. Use when working in a public or soon-to-be-public repo, before…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
github-pr-merge
Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.
resolve-plugins
Curate Claude Code skill / MCP / hook picks against live upstream sources and pin them in .claude/settings.json. Adding a process harness (a paired skill set) is an ordinary pick this door handles. Reads stack from docs/techstack.md, workflow signal from docs/overview.md + existing pins, then live-queries six source…