Anti Hallucination
brycewang-stanford/Auto-Empirical-Research-Skills
ALWAYS activate this skill. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.
CRITICAL SAFETY SKILL — Verify ALL technical claims, API signatures, library methods, code behavior, and factual statements before answering.
Custom licenceAuto-check passed
Install Anti Hallucination
$ npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Aedelon/claude-code-blueprint anti-hallucination --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Aedelon/claude-code-blueprint.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/anti-hallucination .claude/skills/anti-hallucination && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "anti-hallucination" agent skill from https://github.com/Aedelon/claude-code-blueprint/tree/main/skills/anti-hallucination into .claude/skills/anti-hallucination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-hallucination", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Aedelon/claude-code-blueprint/tree/main/skills/anti-hallucinationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Aedelon/claude-code-blueprint anti-hallucination --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Aedelon/claude-code-blueprint.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/anti-hallucination .agents/skills/anti-hallucination && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "anti-hallucination" agent skill from https://github.com/Aedelon/claude-code-blueprint/tree/main/skills/anti-hallucination into .agents/skills/anti-hallucination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-hallucination", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Aedelon/claude-code-blueprint anti-hallucination --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Aedelon/claude-code-blueprint.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/anti-hallucination .cursor/skills/anti-hallucination && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "anti-hallucination" agent skill from https://github.com/Aedelon/claude-code-blueprint/tree/main/skills/anti-hallucination into .cursor/skills/anti-hallucination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-hallucination", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Aedelon/claude-code-blueprint.git --path skills/anti-hallucination--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Aedelon/claude-code-blueprint anti-hallucination --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Aedelon/claude-code-blueprint.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/anti-hallucination .gemini/skills/anti-hallucination && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "anti-hallucination" agent skill from https://github.com/Aedelon/claude-code-blueprint/tree/main/skills/anti-hallucination into .gemini/skills/anti-hallucination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-hallucination", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Aedelon/claude-code-blueprint anti-hallucinationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Aedelon/claude-code-blueprint.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/anti-hallucination .github/skills/anti-hallucination && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "anti-hallucination" agent skill from https://github.com/Aedelon/claude-code-blueprint/tree/main/skills/anti-hallucination into .github/skills/anti-hallucination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-hallucination", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Aedelon/claude-code-blueprint anti-hallucination --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Aedelon/claude-code-blueprint.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/anti-hallucination .opencode/skills/anti-hallucination && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "anti-hallucination" agent skill from https://github.com/Aedelon/claude-code-blueprint/tree/main/skills/anti-hallucination into .opencode/skills/anti-hallucination/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "anti-hallucination", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
anti-hallucination- GitHub stars
- 120
- Token cost
- ~1.1k tokens
- SKILL.md length
- 174 words
- Files
- 1
- Skills in repo
- 8
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
CRITICAL SAFETY SKILL — Verify ALL technical claims, API signatures, library methods, code behavior, and factual statements before answering.
- Works in 3 steps: Identify Claim Type → Execute Verification → Cite Source in Response
- SKILL.md covers Decision Tree (MANDATORY), Forbidden Actions (NEVER), Confidence Declaration and Verification Workflow, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Anti Hallucination is an agent skill from Aedelon/claude-code-blueprint. CRITICAL SAFETY SKILL — Verify ALL technical claims, API signatures, library methods, code behavior, and factual statements before answering. Use Context7, WebSearch, and Read tools to confirm. MUST BE USED PROACTIVELY whenever: writing code that calls any library or API, answering technical questions, stating facts about frameworks or tools, mentioning version numbers, describing function behavior, recommending libraries, comparing technologies, or making any claim that could be wrong. Triggers: "how does X…
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Production-grade Claude Code configuration: skills, agents, hooks, rules, and permissions working as a system.
Example prompts
- “how does X work”
- “what are the arguments for”
- “does this function exist”
- “/anti-hallucination”
Requirements
- Pre-approved tools (allowed-tools): mcp__context7__resolve-library-id, mcp__context7__get-library-docs, mcp__fetch__fetch, WebSearch, WebFetch, Read, Grep
Workflow steps
3 steps, taken from the step headings in SKILL.md.
- Identify Claim Type
- Execute Verification
- Cite Source in Response
What it can do on your machine
Read from SKILL.md and the folder at commit 3bb5099. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
mcp__context7__resolve-library-idmcp__context7__get-library-docsmcp__fetch__fetchWebSearchWebFetchReadGrep
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Anti Hallucination loads about 1.1k tokens when it runs. Until then it costs about 249 tokens; SKILL.md has 174 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 174 words (~1,112 tokens).
- name
- anti-hallucination
- allowed-tools
- mcp__context7__resolve-library-id, mcp__context7__get-library-docs, mcp__fetch__fetch, WebSearch, WebFetch, Read, Grep
Files
Just SKILL.md in skills/anti-hallucination of Aedelon/claude-code-blueprint.
Open the folder on GitHubat commit 3bb5099
Compare with similar skills
Anti Hallucination next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Anti Hallucination this skillAedelon/claude-code-blueprint | 120 | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| Anti Hallucinationbrycewang-stanford/Auto-Empirical-Research-Skills | 4.6k | — | ~1.9k | Automated safety check: Pass | Custom licence | |
| Claimsruvnet/ruflo | 74k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Criticism Self CriticismHughYau/qiushi-skill | 3.8k | — | ~423 | Automated safety check: Pass | MIT | |
| Python Type Safetywshobson/agents | 40k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Python Anti Patternswshobson/agents | 40k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
Claims
ruvnet/ruflo
Claims-based authorization for agents and operations. An agent skill from ruvnet/ruflo.
Criticism Self Criticism
HughYau/qiushi-skill
批评与自我批评：在工作完成、阶段验收、收到批评或同类错误反复出现时，对成果和过程做诚实、具体、基于事实的审视，输出可执行的改进项，并处理外来批评而不辩解。触发信号包括 review、复盘、审查、"帮我看看有没有问题"、"你确定吗"；任务刚开始或只是单步查询时不触发。
Python Type Safety
wshobson/agents
Python type safety with type hints, generics, protocols, and strict type checking.
Python Anti Patterns
wshobson/agents
A skill your agent uses when reviewing Python code for common anti-patterns to avoid.
Crossframe Critical
sickn33/agentic-awesome-skills
Use only when the user explicitly names crossframe-critical for a Chinese structural critique dossier, article plan, or long-form critical essay.
More from Aedelon/claude-code-blueprint
All 8 skills in this repoBrainstorm
Aedelon/claude-code-blueprint
Multi-agent brainstorming and strategic thinking on any complex topic.
Code Patterns
Aedelon/claude-code-blueprint
Reference patterns for REST APIs, pytest/vitest testing, Docker multi-stage builds, GitHub Actions CI/CD, PostgreSQL, TypeScript generics, Python async, and React Server Components.
Commit Message
Aedelon/claude-code-blueprint
Ship workflow: review changes, generate conventional commit messages, push, and create PRs.
Core Protocols
Aedelon/claude-code-blueprint
Debug errors systematically by searching first, then analyzing, then proposing verified solutions.
Research Protocol
Aedelon/claude-code-blueprint
Conduct rigorous research with proper citations (DOI, arXiv, PMID) and source triangulation.
Security Audit
Aedelon/claude-code-blueprint
Proactive security audit: OWASP top 10, dependency vulnerabilities, secrets detection, input validation, auth patterns, and secure defaults.
Questions about Anti Hallucination
What does Anti Hallucination do?
CRITICAL SAFETY SKILL — Verify ALL technical claims, API signatures, library methods, code behavior, and factual statements before answering. Anti Hallucination is an agent skill from Aedelon/claude-code-blueprint. CRITICAL SAFETY SKILL — Verify ALL technical claims, API signatures, library methods, code behavior, and factual statements before answering.
How do I install Anti Hallucination in Claude Code?
Run `npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a claude-code`. Or copy the skill folder (skills/anti-hallucination in Aedelon/claude-code-blueprint) into .claude/skills/anti-hallucination in your project. Claude Code loads it when a task matches its description.
How do I install Anti Hallucination in Codex?
Run `npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a codex`. Or copy the skill folder (skills/anti-hallucination in Aedelon/claude-code-blueprint) into .agents/skills/anti-hallucination in your project. Codex loads it when a task matches its description.
Can I use Anti Hallucination in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Aedelon/claude-code-blueprint --skill anti-hallucination -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/anti-hallucination, .gemini/skills/anti-hallucination, .github/skills/anti-hallucination and .opencode/skills/anti-hallucination in your project.
What does Anti Hallucination need to run?
SKILL.md names no scripts, command-line tools or credentials: Anti Hallucination is instructions for the agent only. Its frontmatter pre-approves these tools: mcp__context7__resolve-library-id, mcp__context7__get-library-docs, mcp__fetch__fetch, WebSearch, WebFetch, Read, Grep.
Does Anti Hallucination access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Anti Hallucination safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Anti Hallucination use?
Anti Hallucination has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Anti Hallucination use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Anti Hallucination?
Skills that share tags, products or a category with Anti Hallucination: Anti Hallucination (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Claims (ruvnet/ruflo, 74k stars), Criticism Self Criticism (HughYau/qiushi-skill, 3.8k stars) and Python Type Safety (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Anti Hallucination?
Aedelon (a GitHub user) maintains it in Aedelon/claude-code-blueprint, which has 120 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on March 4, 2026.
Source: Aedelon/claude-code-blueprint on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.