truth-first

truth-first is a skill for Claude Code from johnrucnapier-sketch/ACGM-for-Claude-Code. It costs 120 tokens per session (2,176 once invoked), scanned C, original, no licence file.

A set of rules for writing technical conclusions and performing irreversible or state-changing operations. It requires evidence tied to file and line locations and restricts unsupported claims.

In plain words
What is it for?
Preparing technical documentation, commit messages, code comments, or reports, and checking evidence before destructive or state-changing actions.
Why use it?
It reduces the risk of presenting guesses as facts or making changes without documented evidence.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the acgm plugin — 4 skills, 4 hooks shipped together

Good fit Preparing technical documentation, commit messages, code comments, or reports, and checking evidence before destructive or state-changing actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/johnrucnapier-sketch/acgm-for-claude-code/truth-first
Install

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.

Any agent
npx skills add johnrucnapier-sketch/ACGM-for-Claude-Code --skill truth-first
Clone the repo
git clone --depth 1 https://github.com/johnrucnapier-sketch/ACGM-for-Claude-Code

Made for: Claude Code.

Or install acgm, the plugin that ships this one along with the rest of its 4 skills, 4 hooks.

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 truth-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/johnrucnapier-sketch/acgm-for-claude-code/truth-first/github.svg)](https://agentmods.dev/skills/johnrucnapier-sketch/acgm-for-claude-code/truth-first)
Your own site
<a href="https://agentmods.dev/skills/johnrucnapier-sketch/acgm-for-claude-code/truth-first"><img src="https://agentmods.dev/badge/skills/johnrucnapier-sketch/acgm-for-claude-code/truth-first/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 truth-first

Your own site · 80×15
<a href="https://agentmods.dev/skills/johnrucnapier-sketch/acgm-for-claude-code/truth-first"><img src="https://agentmods.dev/badge/skills/johnrucnapier-sketch/acgm-for-claude-code/truth-first.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,176 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00120 $0.02176
Opus 5 $0.00060 $0.01088
Sonnet 5 $0.00024 $0.00435
Haiku 4.5 $0.00012 $0.00218

Measured 10d ago against content hash 84084e10d648, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

truth-first scanned grade C 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /the/actual/target
skills/truth-first/SKILL.md · 164 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. 10d ago First seen · 164 lines · 120 tokens per session scan C 84084e10d648

Subscribe to this mod's changes

truth-first is a skill published in the GitHub repository johnrucnapier-sketch/ACGM-for-Claude-Code (1 stars, last pushed 1mo ago), with no licence file. It adds 120 tokens to every session and 2,176 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.