crucible AGENTS.md

Repository instructions for developing the crucible code-audit skill as a general workflow that should work across different projects and technology stacks.

In plain words
What is it for?
Use them when maintaining the crucible skill, especially when changing its findings validator or restructuring its audit phases.
Why use it?
They prevent the skill from becoming tied to one specific codebase and define boundaries for safe changes to its files.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/robcsaszar/crucible/agents-md
Clone the repo
git clone --depth 1 https://github.com/robcsaszar/crucible

Made for: Codex, OpenCode.

Per session 201 This file is loaded in full into every session.
When invoked 201 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00201 $0.00201
Opus 5 $0.00101 $0.00101
Sonnet 5 $0.00040 $0.00040
Haiku 4.5 $0.00020 $0.00020

Measured yesterday against content hash 548a9dd8f119, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crucible AGENTS.md 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 yesterday.

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.

AGENTS.md · 15 lines

What it actually says

AGENTS.md

Mission

This repo publishes the crucible skill: a single skill under skills/crucible/. There is no build, no tests, no runtime of its own. The deliverable is the contents of that one directory. Changes should be judged by: would a stranger who installs this skill into their own project get a correct, generically useful audit workflow out of it, one that doesn't assume Orakl's codebase, stack, or conventions?

Judgment boundaries

ASK:

  • Ask before removing the skill or restructuring its phases; this repo has exactly one skill and no fallback if it regresses.

ALWAYS:

  • Don't let the skill's content drift toward assumptions specific to any one codebase; it needs to read as generic audit guidance for any project.
  • Changes to skills/crucible/scripts/validate-findings.cjs need a matching update to SAFETY.md in the same change.
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. yesterday First seen · 15 lines · 201 tokens per session scan A 548a9dd8f119

Subscribe to this mod's changes

crucible AGENTS.md is an instructions file published in the GitHub repository robcsaszar/crucible (0 stars, last pushed 2d ago), licensed MIT. It adds 201 tokens to every session, about $0.0010 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.