Vercel Composition Patterns
supabase/supabase
React composition patterns that scale. An agent skill from supabase/supabase.
Applies NASA Power of 10 rules for safety-critical verifiable code.
Install Safety Critical Patterns
$ npx skills add athola/claude-night-market --skill safety-critical-patterns -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install athola/claude-night-market safety-critical-patterns --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/athola/claude-night-market.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/pensive/skills/safety-critical-patterns .claude/skills/safety-critical-patterns && 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 "safety-critical-patterns" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/pensive/skills/safety-critical-patterns into .claude/skills/safety-critical-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safety-critical-patterns", 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/athola/claude-night-market/tree/master/plugins/pensive/skills/safety-critical-patternsType 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 athola/claude-night-market --skill safety-critical-patterns -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install athola/claude-night-market safety-critical-patterns --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/pensive/skills/safety-critical-patterns .agents/skills/safety-critical-patterns && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "safety-critical-patterns" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/pensive/skills/safety-critical-patterns into .agents/skills/safety-critical-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safety-critical-patterns", 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 athola/claude-night-market --skill safety-critical-patterns -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install athola/claude-night-market safety-critical-patterns --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/pensive/skills/safety-critical-patterns .cursor/skills/safety-critical-patterns && 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 "safety-critical-patterns" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/pensive/skills/safety-critical-patterns into .cursor/skills/safety-critical-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safety-critical-patterns", 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/athola/claude-night-market.git --path plugins/pensive/skills/safety-critical-patterns--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 athola/claude-night-market --skill safety-critical-patterns -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install athola/claude-night-market safety-critical-patterns --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/pensive/skills/safety-critical-patterns .gemini/skills/safety-critical-patterns && 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 "safety-critical-patterns" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/pensive/skills/safety-critical-patterns into .gemini/skills/safety-critical-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safety-critical-patterns", 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 athola/claude-night-market safety-critical-patternsInstalls 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 athola/claude-night-market --skill safety-critical-patterns -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/pensive/skills/safety-critical-patterns .github/skills/safety-critical-patterns && 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 "safety-critical-patterns" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/pensive/skills/safety-critical-patterns into .github/skills/safety-critical-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safety-critical-patterns", 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 athola/claude-night-market --skill safety-critical-patterns -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install athola/claude-night-market safety-critical-patterns --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/athola/claude-night-market.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/pensive/skills/safety-critical-patterns .opencode/skills/safety-critical-patterns && 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 "safety-critical-patterns" agent skill from https://github.com/athola/claude-night-market/tree/master/plugins/pensive/skills/safety-critical-patterns into .opencode/skills/safety-critical-patterns/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "safety-critical-patterns", 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
safety-critical-patterns- GitHub stars
- 341
- Token cost
- ~1.5k tokens
- SKILL.md length
- 529 words
- Files
- 1
- Skills in repo
- 152
- Repo updated
- First seen
- Licence
- MIT
At a glance
Applies NASA Power of 10 rules for safety-critical verifiable code.
- Works in 10 steps: Restrict Control Flow → Fixed Loop Bounds → No Dynamic Memory After Initialization → …
- Auditing financial
- SKILL.md covers When to Apply, When NOT To Use, The 10 Rules (Adapted) and Rules That May Not Apply, plus 4 more sections
- Calls ruff, mypy and tsc
What it does
Safety Critical Patterns is an agent skill from athola/claude-night-market. Applies NASA Power of 10 rules for safety-critical verifiable code. Use when auditing financial, medical, or high-reliability system code.
Its SKILL.md is about 1.5k 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 Development. The repository describes itself as: 23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context… The licence is MIT.
When your agent uses it
- Auditing financial
- High-reliability system code
Example prompts
- “Use the safety-critical-patterns skill to apply NASA Power of 10 rules for safety-critical verifiable code”
- “/safety-critical-patterns”
Requirements
- Python 3
Workflow steps
10 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 9f3eb00. 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
Shell commands in SKILL.md call:
ruffmypytsc
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
Safety Critical Patterns loads about 1.5k tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 529 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 athola/claude-night-market at commit 9f3eb00, republished under its MIT licence (© athola). 529 words, ~1,482 tokens.
Download SKILL.mdSave it as
.claude/skills/safety-critical-patterns/SKILL.md (or your agent's skills folder).- name
- safety-critical-patterns
- description
- Applies NASA Power of 10 rules for safety-critical verifiable code. Use when auditing financial, medical, or high-reliability system code.
- alwaysApply
- false
- category
- code-quality
- tags
- safety, defensive-coding, assertions, NASA, robustness, verification
- complexity
- intermediate
- model_hint
- standard
- estimated_tokens
- 600
- dependencies
- pensive:code-refinement, imbue:review-core, imbue:structured-output
Safety-Critical Coding Patterns
Guidelines adapted from NASA's Power of 10 rules for safety-critical software.
When to Apply
Full rigor: Safety-critical systems, financial transactions, data integrity code Selective application: Business logic, API handlers, core algorithms Light touch: Scripts, prototypes, non-critical utilities
"Match rigor to consequence" - The real engineering principle
When NOT To Use
- Ordinary application code, where these defensive checks become the
bloat that
prefer-invariants-over-fallbackstargets (useconserve:code-quality-principles)
The 10 Rules (Adapted)
1. Restrict Control Flow
Avoid goto, setjmp/longjmp, and limit recursion.
Why: Ensures acyclic call graphs that tools can verify. Adaptation: Recursion acceptable with provable termination (tail recursion, bounded depth).
2. Fixed Loop Bounds
All loops should have verifiable upper bounds.
# Good - bound is clear
for i in range(min(len(items), MAX_ITEMS)):
process(item)
# Risky - unbounded
while not_done: # When does this end?
process_next()Adaptation: Document expected bounds; add safety limits on potentially unbounded loops.
3. No Dynamic Memory After Initialization
Avoid heap allocation in critical paths after startup.
Why: Prevents allocation failures at runtime. Adaptation: Pre-allocate pools; use object reuse patterns in hot paths.
4. Function Length ~60 Lines
Functions should fit on one screen/page.
Why: Cognitive limits on comprehension remain valid. Adaptation: Flexible for declarative code; strict for complex logic.
5. Assertion Density
Include defensive assertions documenting expectations.
def transfer_funds(from_acct, to_acct, amount):
assert from_acct != to_acct, "Cannot transfer to same account"
assert amount > 0, "Transfer amount must be positive"
assert from_acct.balance >= amount, "Insufficient funds"
# ... implementationAdaptation: Focus on boundary conditions and invariants, not arbitrary quotas.
6. Minimal Variable Scope
Declare variables at narrowest possible scope.
# Good - scoped tightly
for item in items:
total = calculate(item) # Only exists in loop
results.append(total)
# Avoid - unnecessarily broad
total = 0 # Why is this outside?
for item in items:
total = calculate(item)
results.append(total)7. Check Return Values and Parameters
Validate inputs; never ignore return values.
# Good
result = parse_config(path)
if result is None:
raise ConfigError(f"Failed to parse {path}")
# Bad
parse_config(path) # Ignored return8. Limited Preprocessor/Metaprogramming
Restrict macros, decorators, and code generation.
Why: Makes static analysis possible. Adaptation: Document metaprogramming thoroughly; prefer explicit over magic.
9. Pointer/Reference Discipline
Limit indirection levels; be explicit about ownership.
Adaptation: Use type hints, avoid deep nesting of optionals, prefer immutable data.
10. Enable All Warnings
Compile/lint with strictest settings from day one.
# Python
ruff check --select=ALL
mypy --strict
# TypeScript
tsc --strict --noImplicitAnyRules That May Not Apply
| Rule | When to Relax |
|---|---|
| No recursion | Tree traversal, parser combinators with bounded depth |
| No dynamic memory | GC languages, short-lived processes |
| 60-line functions | Declarative configs, state machines |
| No function pointers | Callbacks, event handlers, strategies |
Show full SKILL.md (217 more words)Show less
Integration
Reference this skill from:
pensive:code-refinement- Clean code and quality dimensionsanctum:pr-review- Code quality phase/harden- composed in the hardening pipeline/full-review safety-critical- focused entry point, and an auto-detection row when assertion density is low, loops are unbounded, or recursion lacks a termination proof
Violation Output Format
For each rule violation, report:
Rule N: <rule name>
Location: file.py:42
Anchor: `<verbatim source text at line 42>`
Issue: <what violates the rule>
Fix: <concrete remediation>Verify Findings Are Grounded (safety-critical:findings-verified)
Write findings to .review/findings.json, run the citation verifier
(Skill(imbue:review-core) Step 5), and drop or label UNVERIFIED any
the verifier rejects.
Exit Criteria
- Each of the 10 rules has an explicit verdict for the target (applies / violated / not applicable), not a silent skip
- Every reported violation cites a concrete
file:lineand the rule number it breaks - Rules deemed not applicable name the reason (e.g. "no dynamic allocation in this module") rather than being omitted
- Loops flagged under Rule 2 are checked for a statically provable upper bound; unbounded loops are reported
- Recursion flagged under Rule 1 is reported when it lacks a termination argument
- A summary states whether the target is suitable for safety-critical use, or which rules block that judgment
- Every reported violation carries a
Location+ verbatimAnchorconfirmed bycitation_verifier.py(exit0), or unverified violations were dropped or labeledUNVERIFIED.
Sources
- NASA JPL Power of 10 Rules (Gerard Holzmann, 2006)
- MISRA C Guidelines
- HN discussion insights on practical application
© athola, 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 plugins/pensive/skills/safety-critical-patterns of athola/claude-night-market.
Open the folder on GitHubat commit 9f3eb00
Compare with similar skills
Safety Critical Patterns 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 |
|---|---|---|---|---|---|---|
| Safety Critical Patterns this skillathola/claude-night-market | 341 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Vercel Composition Patternssupabase/supabase | 111k | 58 repos | ~726 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Typescript Advanced Typesrolling-scopes/rsschool-app | 10k | 25 repos | ~4.2k | Automated safety check: Pass | MPL-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 4 repos | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Typescript Advanced Types
rolling-scopes/rsschool-app
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Code Review Checklist
shareAI-lab/learn-claude-code
Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.
Greploop
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
More from athola/claude-night-market
All 152 skills in this repoNight Market Diagnostics Toolkit
athola/claude-night-market
Run and interpret repo diagnostic scripts (ratchets, validators, token stats).
Skills Eval
athola/claude-night-market
Evaluate Claude skill quality through auditing. An agent skill from athola/claude-night-market.
Agent Teams
athola/claude-night-market
Coordinates Claude agent teams via filesystem protocol. An agent skill from athola/claude-night-market.
Delegation Core
athola/claude-night-market
Delegates execution to eight CLIs (Gemini, Qwen, MiniMax, GLM, Muse, Codex, OpenCode, Glimmer).
Elegant Code
athola/claude-night-market
Guide minimal code via a decision ladder with full safety, edge, and negative-case coverage.
Skill Library Mission
athola/claude-night-market
Build a project skill library in .claude/skills/ via discovery, parallel authoring, and review.
Related
Categories
Questions about Safety Critical Patterns
What does Safety Critical Patterns do?
Applies NASA Power of 10 rules for safety-critical verifiable code. Safety Critical Patterns is an agent skill from athola/claude-night-market. Applies NASA Power of 10 rules for safety-critical verifiable code.
When should I use Safety Critical Patterns?
Safety Critical Patterns fits situations like: auditing financial; high-reliability system code.
How do I install Safety Critical Patterns in Claude Code?
Run `npx skills add athola/claude-night-market --skill safety-critical-patterns -a claude-code`. Or copy the skill folder (plugins/pensive/skills/safety-critical-patterns in athola/claude-night-market) into .claude/skills/safety-critical-patterns in your project. Claude Code loads it when a task matches its description.
How do I install Safety Critical Patterns in Codex?
Run `npx skills add athola/claude-night-market --skill safety-critical-patterns -a codex`. Or copy the skill folder (plugins/pensive/skills/safety-critical-patterns in athola/claude-night-market) into .agents/skills/safety-critical-patterns in your project. Codex loads it when a task matches its description.
Can I use Safety Critical Patterns 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 athola/claude-night-market --skill safety-critical-patterns -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/safety-critical-patterns, .gemini/skills/safety-critical-patterns, .github/skills/safety-critical-patterns and .opencode/skills/safety-critical-patterns in your project.
What does Safety Critical Patterns need to run?
Going by SKILL.md and its folder, Safety Critical Patterns needs the command-line tools its instructions call (ruff, mypy and tsc). Our summary lists: Python 3.
Does Safety Critical Patterns 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 Safety Critical Patterns 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 Safety Critical Patterns use?
Safety Critical Patterns 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 Safety Critical Patterns use?
About 1.5k tokens (SKILL.md is roughly 5.9k 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 Safety Critical Patterns?
Skills that share tags, products or a category with Safety Critical Patterns: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Safety Critical Patterns?
athola (a GitHub user) maintains it in athola/claude-night-market, which has 341 GitHub stars. The repository holds 152 skills in this directory. The repository was last updated on October 9, 2026.
Source: athola/claude-night-market on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.