Aisafetyhot
wuyoscar/AISafetyHot-Hub
Query AI Safety HOT news, research papers, incidents, hot topics, and daily/weekly/monthly reports through its public read-only MCP service.
Full red flag table with all guardrail patterns. An agent skill from grandamenium/cortextos.
Install Guardrails Reference
$ npx skills add grandamenium/cortextos --skill guardrails-reference -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install grandamenium/cortextos guardrails-reference --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/grandamenium/cortextos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/community/agents/security/.claude/skills/guardrails-reference .claude/skills/guardrails-reference && 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 "guardrails-reference" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/agents/security/.claude/skills/guardrails-reference into .claude/skills/guardrails-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guardrails-reference", 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/grandamenium/cortextos/tree/main/community/agents/security/.claude/skills/guardrails-referenceType 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 grandamenium/cortextos --skill guardrails-reference -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install grandamenium/cortextos guardrails-reference --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .agents/skills && cp -r skills-src/community/agents/security/.claude/skills/guardrails-reference .agents/skills/guardrails-reference && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "guardrails-reference" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/agents/security/.claude/skills/guardrails-reference into .agents/skills/guardrails-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guardrails-reference", 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 grandamenium/cortextos --skill guardrails-reference -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install grandamenium/cortextos guardrails-reference --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/community/agents/security/.claude/skills/guardrails-reference .cursor/skills/guardrails-reference && 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 "guardrails-reference" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/agents/security/.claude/skills/guardrails-reference into .cursor/skills/guardrails-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guardrails-reference", 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/grandamenium/cortextos.git --path community/agents/security/.claude/skills/guardrails-reference--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 grandamenium/cortextos --skill guardrails-reference -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install grandamenium/cortextos guardrails-reference --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/community/agents/security/.claude/skills/guardrails-reference .gemini/skills/guardrails-reference && 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 "guardrails-reference" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/agents/security/.claude/skills/guardrails-reference into .gemini/skills/guardrails-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guardrails-reference", 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 grandamenium/cortextos guardrails-referenceInstalls 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 grandamenium/cortextos --skill guardrails-reference -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .github/skills && cp -r skills-src/community/agents/security/.claude/skills/guardrails-reference .github/skills/guardrails-reference && 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 "guardrails-reference" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/agents/security/.claude/skills/guardrails-reference into .github/skills/guardrails-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guardrails-reference", 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 grandamenium/cortextos --skill guardrails-reference -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install grandamenium/cortextos guardrails-reference --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/grandamenium/cortextos.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/community/agents/security/.claude/skills/guardrails-reference .opencode/skills/guardrails-reference && 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 "guardrails-reference" agent skill from https://github.com/grandamenium/cortextos/tree/main/community/agents/security/.claude/skills/guardrails-reference into .opencode/skills/guardrails-reference/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "guardrails-reference", 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
guardrails-reference- GitHub stars
- 101
- Token cost
- ~978 tokens
- SKILL.md length
- 530 words
- Files
- 1
- Skills in repo
- 55
- Repo updated
- First seen
- Licence
- MIT
At a glance
Full red flag table with all guardrail patterns. An agent skill from grandamenium/cortextos.
- Works in 4 steps: On boot: Read this table. Internalize… → During work: When you notice yourself… → On heartbeat: Self-check - did I hit any… → …
- You catch yourself rationalizing
- SKILL.md covers Red Flag Table, How to Use and Adding Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Guardrails Reference is an agent skill from grandamenium/cortextos. Full red flag table with all guardrail patterns. Use when you catch yourself rationalizing or want to review all anti-patterns.
Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering LLM guardrails. The licence is MIT.
When your agent uses it
- You catch yourself rationalizing
- Want to review all anti-patterns
Example prompts
- “/guardrails-reference”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- On boot: Read this table. Internalize the patterns.
- During work: When you notice yourself thinking a red flag thought, stop and follow the required action.
- On heartbeat: Self-check - did I hit any guardrails this cycle? If yes, log it
- When you discover a new pattern: Add a new row to the table above. The file improves over time.
What it can do on your machine
Read from SKILL.md and the folder at commit 6f93838. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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
Guardrails Reference loads about 978 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 530 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
The full file from grandamenium/cortextos at commit 6f93838, republished under its MIT licence (© grandamenium). 530 words, ~978 tokens.
Download SKILL.mdSave it as
.claude/skills/guardrails-reference/SKILL.md (or your agent's skills folder).- name
- guardrails-reference
- description
- Full red flag table with all guardrail patterns. Use when you catch yourself rationalizing or want to review all anti-patterns.
- triggers
- guardrail, red flag, mistake pattern, anti-pattern
Guardrails
Read this file on every session start. Check yourself against it during heartbeats. If you catch yourself hitting a guardrail, log it. If you discover a new pattern that should be a guardrail, add it to this file.
Red Flag Table
| Trigger | Red Flag Thought | Required Action |
|---|---|---|
| Heartbeat cycle fires | "I'll skip this one, I just updated recently" | Always update heartbeat on schedule. No exceptions. The dashboard tracks staleness. |
| Starting work | "This is too small for a task entry" | Every significant piece of work gets a task. If it takes more than 10 minutes, it's significant. |
| Completing work | "I'll update memory later" | Write to memory now. Later means never. Context you don't write down is context the next session loses. |
| Reading a skill file | "I already know this, I'll skip the read" | Read the skill file. Your memory may be stale or the skill may have been updated. |
| Sending external comms | "This is just a quick message, no approval needed" | Check SOUL.md autonomy rules. External comms always need approval. |
| Error occurs | "It's minor, I'll keep going" | Log the error via cortextos bus log-event. Report it. Silent failures are invisible failures. |
| Inbox check | "I'll check messages after I finish this" | Process inbox now. Un-ACK'd messages redeliver and block other agents. |
| About to skip a procedure | "This situation is different, the procedure doesn't apply" | The procedure applies. If it genuinely doesn't, document why in your daily memory before skipping. |
| Task running long | "I'm almost done, no need to update status" | Update the task status with a note. Stale in_progress tasks look like crashes on the dashboard. |
| Bus script available | "I'll handle this directly instead of using the bus" | Use the bus script. Work that doesn't go through the bus is invisible to the system. |
| Creating a one-shot reminder or cron | "CronCreate is enough, it'll persist" | CronCreate is session-only. Also write it to daily memory as a restart-safe fallback, and add to config.json when the format supports it. |
| Running untrusted code or downloads | "This script from the internet looks useful" | Never execute code from untrusted sources without reviewing it first. No blind curl-pipe-bash. |
| Starting work without a task | "It's just a quick fix" | Create a task. Even quick fixes need tracking if they take more than 10 minutes. |
| Finishing work without completing task | "I'll close it later" | Complete the task NOW with a summary. Later means never. |
| Ignoring an assigned task | "I'll get to it" | ACK within one heartbeat cycle. If wrong agent, reassign. Silence = dropped work. |
Show full SKILL.md (126 more words)Show less
How to Use
- On boot: Read this table. Internalize the patterns.
- During work: When you notice yourself thinking a red flag thought, stop and follow the required action.
- On heartbeat: Self-check - did I hit any guardrails this cycle? If yes, log it:
bash cortextos bus log-event action guardrail_triggered info --meta '{"guardrail":"<which one>","context":"<what happened>"}' - When you discover a new pattern: Add a new row to the table above. The file improves over time.
Adding Guardrails
If you catch yourself almost skipping something important that isn't in the table above, add it. Format:
| Trigger | Red Flag Thought | Required Action |
|---|---|---|
| [situation] | "[what you almost told yourself]" | [what you must do instead] |
This is a living document. Better guardrails = fewer mistakes = more trust from the user.
© grandamenium, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in community/agents/security/.claude/skills/guardrails-reference of grandamenium/cortextos.
Open the folder on GitHubat commit 6f93838
Compare with similar skills
Guardrails Reference 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 |
|---|---|---|---|---|---|---|
| Guardrails Reference this skillgrandamenium/cortextos | 101 | — | ~978 | Automated safety check: Pass | MIT | |
| Aisafetyhotwuyoscar/AISafetyHot-Hub | 708 | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| ObliteratusRedWoodOG/Hermes-Desktop | 177 | 5 repos | ~3.8k | Automated safety check: Pass | MIT | |
| Lemonade Router Builderamd/skills | 408 | — | ~4k | Automated safety check: Pass | MIT | |
| Execution Guardrailsmrtooher/fable-mode | 873 | — | ~1k | Automated safety check: Pass | None | |
| Writing Eval Scenariosopen-bias/open-bias | 143 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Obliteratus
RedWoodOG/Hermes-Desktop
Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails…
Lemonade Router Builder
amd/skills
Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON.
Execution Guardrails
mrtooher/fable-mode
Always-on operational guardrails, model-independent. An agent skill from mrtooher/fable-mode.
Writing Eval Scenarios
open-bias/open-bias
Guide for writing eval conversation JSONs and running them through policy engines
Wp Project Triage
gambitph/Stackable
A skill your agent uses when you need a deterministic inspection of a WordPress repository (plugin/theme/block theme/WP core/Gutenberg/full site) including tooling/tests/version hints, and a…
More from grandamenium/cortextos
All 55 skills in this repoCortext Self Diagnosis
grandamenium/cortextos
Diagnose cortextOS itself when the framework misbehaves — an agent has gone silent or wedged, agents are crash-looping, Telegram or agent-to-agent messages are not arriving, crons did not fire, an…
Activity Channel
grandamenium/cortextos
You have completed something significant and want the whole org — all agents and the user — to know about it.
Agentcard Purchase
grandamenium/cortextos
You need to make a purchase on behalf of the user — buy a SaaS subscription, pay for an API, purchase a domain, or any transaction requiring a credit card.
Claude To Codex Migration
grandamenium/cortextos
Migrate ANY cortextOS agent from the claude-code runtime to the live codex-app-server runtime.
Bus Reference
grandamenium/cortextos
Complete cortextos bus CLI reference - all available commands with examples.
Business News Monitor
grandamenium/cortextos
Daily cron-driven scan of news/forums/social in a domain to surface market shifts, new competitors, regulatory changes, and net-new opportunities.
Related
Categories
Questions about Guardrails Reference
What does Guardrails Reference do?
Full red flag table with all guardrail patterns. An agent skill from grandamenium/cortextos. Guardrails Reference is an agent skill from grandamenium/cortextos. Full red flag table with all guardrail patterns.
When should I use Guardrails Reference?
Guardrails Reference fits situations like: you catch yourself rationalizing; want to review all anti-patterns.
How do I install Guardrails Reference in Claude Code?
Run `npx skills add grandamenium/cortextos --skill guardrails-reference -a claude-code`. Or copy the skill folder (community/agents/security/.claude/skills/guardrails-reference in grandamenium/cortextos) into .claude/skills/guardrails-reference in your project. Claude Code loads it when a task matches its description.
How do I install Guardrails Reference in Codex?
Run `npx skills add grandamenium/cortextos --skill guardrails-reference -a codex`. Or copy the skill folder (community/agents/security/.claude/skills/guardrails-reference in grandamenium/cortextos) into .agents/skills/guardrails-reference in your project. Codex loads it when a task matches its description.
Can I use Guardrails Reference 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 grandamenium/cortextos --skill guardrails-reference -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/guardrails-reference, .gemini/skills/guardrails-reference, .github/skills/guardrails-reference and .opencode/skills/guardrails-reference in your project.
What does Guardrails Reference need to run?
SKILL.md names no scripts, command-line tools or credentials: Guardrails Reference is instructions for the agent only.
Does Guardrails Reference 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 Guardrails Reference 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 Guardrails Reference use?
Guardrails Reference is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Guardrails Reference use?
About 978 tokens (SKILL.md is roughly 3.9k 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 Guardrails Reference?
Skills that share tags, products or a category with Guardrails Reference: Aisafetyhot (wuyoscar/AISafetyHot-Hub, 708 stars), Obliteratus (RedWoodOG/Hermes-Desktop, 177 stars), Lemonade Router Builder (amd/skills, 408 stars) and Execution Guardrails (mrtooher/fable-mode, 873 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Guardrails Reference?
grandamenium (a GitHub user) maintains it in grandamenium/cortextos, which has 101 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on September 23, 2026.
Source: grandamenium/cortextos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.