latitude-llm: Skill for Claude Code

.agents/skills/toolchain-commands/SKILL.md

toolchain-commands is a skill for Claude Code, Codex from latitude-dev/latitude-llm. It costs 46 tokens per session (1,551 once invoked), scanned B, original, MIT.

A repository guide for installing dependencies and running development, build, test, lint, type-check, Git-hook, Docker, and local-service commands. It documents the project’s required versions and tools, including Node.js, pnpm, Turbo, Biome, TypeScript, and Vitest.

In plain words
What is it for?
Use it when preparing a clone, installing packages, running the development server, building, linting, type-checking, running all or selected tests, using Git hooks, or starting Docker-backed services.
Why use it?
It prevents commands from being run with the wrong runtime, package manager, or project tool. That reduces avoidable failures caused by version mismatches or incorrect scripts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is latitude-dev/latitude-llm's own configuration. It tells Claude Code and Codex how to work on latitude-llm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything latitude-llm configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is pnpm --filter ./apps/api test.

About the project

Latitude is an open-source platform for monitoring AI agents by collecting execution traces, grouping failures, dispatching coding agents to make fixes, and replaying failures to verify them. Teams use it to observe agent behavior, investigate errors, and monitor whether fixes prevent regressions. The catalogue entries include skills, instructions, and an MCP server for working with Latitude.

latitude-dev/latitude-llm · 4,632 stars · on GitHub · latitude.so

Reuse

Borrowing it

Nothing to install: this file belongs to latitude-dev/latitude-llm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/latitude-dev/latitude-llm/development/.agents/skills/toolchain-commands/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/latitude-dev/latitude-llm

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for toolchain-commands

README.md
[![agentmods](https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/toolchain-commands/github.svg)](https://agentmods.dev/skills/latitude-dev/latitude-llm/toolchain-commands)
Your own site
<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/toolchain-commands"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/toolchain-commands/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.

agentmods 80×15 button for toolchain-commands

Your own site · 80×15
<a href="https://agentmods.dev/skills/latitude-dev/latitude-llm/toolchain-commands"><img src="https://agentmods.dev/badge/skills/latitude-dev/latitude-llm/toolchain-commands.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,551 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 3
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • high Privilege Escalation · line 92
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Tool Misuse · line 98
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
  • medium Privilege Escalation · line 108
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 109
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.01551
Opus 5 $0.00023 $0.00776
Sonnet 5 $0.00009 $0.00310
Haiku 4.5 $0.00005 $0.00155

Measured 9d ago against content hash b3389b48eb64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

toolchain-commands scanned grade B with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo dockerd &>/dev/null & # if the daemon is not already running

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Web | 3000 | `curl http://localhost:3000` (redirect to `/login`) |
.agents/skills/toolchain-commands/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Toolchain, commands, and CI

When to use: Installing dependencies, running dev/build/test/lint, filtering packages, single-test runs, git hooks, preparing a clone (.env.development / .env.test), or Docker-backed local services and dev servers.

Stack (summary)

  • Runtime: Node.js 25 via mise.toml (also engines in root package.json). Use mise install / mise exec so Vitest and Uint8Array.fromHex / toHex match production; Node 22 lacks those APIs and will fail tests that touch @repo/utils crypto helpers.
  • Package manager: package.json packageManager field (e.g. pnpm). Install deps: pnpm install
  • Task runner: turbo via root scripts
  • Lint/format: Biome (@biomejs/biome 1.9.x)
  • TypeScript: 6.0.x + TypeScript 7 beta (@typescript/native-preview) for typechecking. pnpm typecheck runs tsgo (the native preview binary) — never invoke tsc directly in scripts or docs.
  • Bundler: tsdown (replaces the deprecated tsup). App builds and library DTS emission run under tsdown.
  • Tests: Vitest 3.x
  • Core logic: Effect TS primitives
  • Postgres ORM: Drizzle
  • API/ingest boundaries: Hono
  • Web app: TanStack Start + React

Top-level commands (repo root)

  • pnpm dev — run all workspace dev tasks via Turbo
  • pnpm build — run all workspace builds
  • pnpm check — run all workspace lint and format check scripts
  • pnpm typecheck — run all workspace typechecks
  • pnpm test — run all workspace tests
  • pnpm hooks — configure local git hooks for this clone

Searching the repo

grep is a shadowed shell function here, and some sources (e.g. packages/domain/spans/src/otlp/transform.ts) trip binary-file detection because of lone surrogates, which silently suppresses matches. Use command grep -a, or the dedicated search tools, before concluding a string is absent.

Git hooks (pre-commit)

  • Pre-commit hook lives at .husky/pre-commit
  • Pre-commit runs: pnpm check, pnpm typecheck, and pnpm knip
  • Hooks are auto-configured on dependency install via root prepare script (pnpm hooks)
  • Existing clones should run pnpm hooks once to configure core.hooksPath and hook permissions

Read the full file on GitHub · 144 lines

Changes

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.

  1. 9d ago First seen · 144 lines · 46 tokens per session scan B b3389b48eb64

Subscribe to this mod's changes

toolchain-commands is a skill published in the GitHub repository latitude-dev/latitude-llm (4,632 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,551 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.