hallucination-prevention

hallucination-prevention is a skill for Claude Code, Codex from magiccloudflash/opencode-skill-hallucination-prevention. It costs 33 tokens per session (1,837 once invoked), scanned C, original, MIT.

A set of working rules for checking information against files, command results, and other evidence before relying on it or reporting it.

In plain words
What is it for?
Use it after edits and commands, before claiming that tests or builds work, and whenever earlier results or file contents need confirmation.
Why use it?
It reduces unsupported claims caused by stale memory, mistaken assumptions, or unverified AI output.

Skill for Claude CodeCodex

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 skills/magiccloudflash/opencode-skill-hallucination-prevention/hallucination-prevention
Any agent
npx skills add magiccloudflash/opencode-skill-hallucination-prevention --skill hallucination-prevention
Clone the repo
git clone --depth 1 https://github.com/magiccloudflash/opencode-skill-hallucination-prevention

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 hallucination-prevention

README.md
[![agentmods](https://agentmods.dev/badge/skills/magiccloudflash/opencode-skill-hallucination-prevention/hallucination-prevention.svg)](https://agentmods.dev/skills/magiccloudflash/opencode-skill-hallucination-prevention/hallucination-prevention)
Your own site
<a href="https://agentmods.dev/skills/magiccloudflash/opencode-skill-hallucination-prevention/hallucination-prevention"><img src="https://agentmods.dev/badge/skills/magiccloudflash/opencode-skill-hallucination-prevention/hallucination-prevention.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,837 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 5.1 $0.00033 $0.01837
Opus 5 $0.00016 $0.00919
Sonnet 5 $0.00007 $0.00367
Haiku 4.5 $0.00003 $0.00184

Measured 5d ago against content hash 4fa86ba929cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade C, and why

hallucination-prevention 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 5d 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.

Review for: rm -rf, force push, DROP/DELETE, format, mkfs, sudo. Ask first. Prefer --dry-run.
hallucination-prevention/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Memory protocol — context integrity

State tracking

  • After each edit: re-read the file to confirm
  • After 5+ tool calls: re-read ALL modified files, verify accumulated state matches expectations
  • After command execution: compare output against what was expected. If mismatch, investigate.
  • After moving to a new task: re-read ALL files relevant to the current context
  • Trust re-read data only — never trust memory of earlier observations

Before claiming recall

  • "As I saw earlier in file X..." → re-read file X first
  • "The earlier error was..." → reproduce or re-read the actual error output
  • "I already verified that..." → re-verify by re-reading/running
  • If you cannot re-read/re-run: say "I recall earlier but need to verify"

Reality checkpoint

Before stating any output/result/state, verify:

  1. Can I re-read the relevant file right now?
  2. Can I re-run the relevant command right now?
  3. If no to both: state "based on earlier session recall, not re-verified"

Hallucination defense

Universal verification triggers

Any of these trigger mandatory re-verification:

  • You're about to say "tests pass", "lint is clean", "it compiles", "it works"
  • You're about to quote an error message from memory
  • You're about to reference a function/class you haven't grep'd
  • You're about to claim a file exists at a path you haven't listed
  • You're about to say "this package supports..." without checking docs/source
  • You're about to provide a URL you haven't visited
  • You're about to name a commit/PR/issue from memory

Output provenance

Every claim about output must answer: "How do I know this?"

  • Live execution: "I just ran npm test and got: ..."
  • Re-read confirmation: "I re-read file.ts and it contains: ..."
  • Fresh grep: "I grep'd for the function and found it at line X"
  • Memory disclaimer: "I saw this earlier but have not re-verified"

Hallucination taxonomy

A-Factual(unverified)↦verify source/run | B-Structural(fake paths)↦ls/glob | C-Behavioral(assumed)↦execute | D-External(fake APIs)↦check docs | E-Outcome(imagined)↦run+show | F-Temporal(wrong ver)↦check ver | G-Authority(pretended)↦actually do | H-Reference(fake URL/id)↦visit/unverified

Read the full file on GitHub · 130 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. 5d ago First seen · 130 lines · 33 tokens per session scan C 4fa86ba929cf

Subscribe to this mod's changes

hallucination-prevention is a skill published in the GitHub repository magiccloudflash/opencode-skill-hallucination-prevention (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,837 once invoked, about $0.0002 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.

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

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

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens