ground-truth

ground-truth is a skill for Claude Code from V-Songbird/slag. It costs 151 tokens per session (710 once invoked), scanned A, original, MIT.

A reference workflow for retrieving current official Claude Code documentation and a bundled reference for certain host tools. It returns source material about how the coding assistant works.

In plain words
What is it for?
Use it when checking Claude Code features, settings, command-line options, hooks, plug-ins, agents, skills, MCP tools, or the Agent SDK.
Why use it?
It provides authoritative details for questions about Claude Code instead of relying on memory. This is useful when names, options, events, or behavior may have changed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the verity plugin — 1 skill shipped together

Good fit Use it when checking Claude Code features, settings, command-line options, hooks, plug-ins, agents, skills, MCP tools, or the Agent SDK.

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add V-Songbird/slag
Claude Code
/plugin install verity

Made for: Claude Code.

Or install verity, the plugin that ships this one along with the rest of its 1 skill.

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 ground-truth

README.md
[![agentmods](https://agentmods.dev/badge/skills/v-songbird/slag/ground-truth/github.svg)](https://agentmods.dev/skills/v-songbird/slag/ground-truth)
Your own site
<a href="https://agentmods.dev/skills/v-songbird/slag/ground-truth"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/ground-truth/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 ground-truth

Your own site · 80×15
<a href="https://agentmods.dev/skills/v-songbird/slag/ground-truth"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/ground-truth.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 151 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 710 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00151 $0.00710
Opus 5 $0.00076 $0.00355
Sonnet 5 $0.00030 $0.00142
Haiku 4.5 $0.00015 $0.00071

Measured 9d ago against content hash cfcef6b91f11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ground-truth 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.

verity/skills/ground-truth/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verity — ground-truth

Fetch and return the authoritative source for a Claude Code question. Two fetch paths depending on what is being asked.

Path A — Official Claude Code docs (live fetch)

Use for any question about Claude Code features, behavior, settings, permissions, hooks, CLI, plugins, agents, skills, MCP, or the Agent SDK.

Step 1 — discover the right page:

WebFetch https://code.claude.com/llms.txt

This returns a Markdown index of all doc pages with titles and one-line descriptions. Scan it to find the slug(s) that match the question. Each entry is formatted as:

- [Page Title](https://code.claude.com/docs/en/{slug}.md): Brief description

Step 2 — fetch the page as raw Markdown:

WebFetch https://code.claude.com/docs/en/{slug}.md

Returns raw Markdown source — not rendered HTML. Quote the relevant section(s) in your response. Only fetch additional pages if the first does not fully answer the question.

Fallback: If no slug in llms.txt clearly matches the question, fetch https://code.claude.com/docs/en/overview.md to orient, then try the closest slug from the index.

Path B — Undocumented host/session MCP tools (bundled reference)

Use for questions about spawn_task, dismiss_task, mark_chapter, read_widget_context, show_widget, visualize, ccd_session, ccd_session_mgmt, scheduled-tasks, ccd_directory, or any other session-injected host tool.

Read ${CLAUDE_PLUGIN_ROOT}/references/host-mcp-tools.md

This file is canonical truth. Do not attempt live introspection of the session toolset to answer these questions — the bundled reference is sourced from direct parameter-schema observation, version-labeled, and more reliable than runtime inference. If a tool the user asks about is not listed in the file, say so explicitly and cite the observation date from the file header so the user knows the reference may be incomplete for a newer harness version.

Source citation (required)

Always end your answer with a citation so the user knows what was fetched and when:

Read the full file on GitHub · 63 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 · 63 lines · 151 tokens per session scan A cfcef6b91f11

Subscribe to this mod's changes

ground-truth is a skill published in the GitHub repository V-Songbird/slag (1 stars, last pushed 4d ago), licensed MIT. It adds 151 tokens to every session and 710 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens