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.
npx skills add rjmurillo/ai-agents --skill golden-principlesgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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.
[](https://agentmods.dev/skills/rjmurillo/ai-agents/golden-principles)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/golden-principles"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/golden-principles/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/golden-principles"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/golden-principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.01441 |
| Opus 5.5 | $0.00022 | $0.00576 |
| Sonnet 5.5 | $0.00011 | $0.00288 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
golden-principles 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 1mo 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.
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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Golden Principles
Scan the repository for violations of mechanically enforced golden principles. Produces remediation instructions that agents can act on directly.
Inspired by OpenAI Harness Engineering:
"We started encoding what we call 'golden principles' directly into the repository and built a recurring cleanup process."
Triggers
| Trigger Phrase | Operation |
|---|---|
scan golden principles |
Full principle compliance scan |
check principle compliance |
Scan with summary report |
golden principle violations |
Scan and list violations |
run garbage collection |
Deep scan with fix-up recommendations |
audit principles |
Scan specific rules only |
When to Use
Use this skill when:
- Preparing a PR for submission (catch violations early)
- Running periodic garbage collection scans
- Auditing a domain or directory for compliance
- Adding new files to the repository
Use taste-lints instead when:
- Checking code-level invariants only (file size, naming, complexity)
- Running pre-commit checks on staged files
Use quality-grades instead when:
- Grading domains across architectural layers
- Producing quality trend reports
Process
- Run
python3 .claude/skills/golden-principles/scripts/scan_principles.pywith target - Review AGENT_REMEDIATION blocks in output
- Apply suggested fixes
- Re-run to confirm compliance
Usage
# Scan entire repository
python3 .claude/skills/golden-principles/scripts/scan_principles.py
# Scan specific directory
python3 .claude/skills/golden-principles/scripts/scan_principles.py --directory .claude/skills/
# Scope to a pull request diff (only files changed vs the base branch)
python3 .claude/skills/golden-principles/scripts/scan_principles.py --diff-scope "origin/$BASE_BRANCH"
# Run specific rules only
python3 .claude/skills/golden-principles/scripts/scan_principles.py --rules script-language,skill-frontmatter
# JSON output for tooling
python3 .claude/skills/golden-principles/scripts/scan_principles.py --format json
# Write results to file
python3 .claude/skills/golden-principles/scripts/scan_principles.py --output scan-results.json --format json
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/design-code-qualities.md 2.8 KB
- references/design-dry-principle.md 2.3 KB
- references/design-programming-by-intention.md 2.3 KB
- references/design-separation-of-concerns.md 2.2 KB
- references/design-solid-principles.md 2.4 KB
- scripts/scan_principles_core.py 19 KB runs code
- scripts/scan_principles.py 15 KB runs code
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.
- 1mo ago Changed · +6 lines 234e422afa55
- 1mo ago First seen · 141 lines · 54 tokens per session scan A a7aaeeabf103
golden-principles is a skill published in the GitHub repository rjmurillo/ai-agents (49 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 1,441 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
review-remote
Review open PR/MR and publish findings.
phoenix-review
Review completed work against the Intent Contract's acceptance criteria using objective evidence, not opinion — re-run every check, confirm no regressions, inspect the tamper-evident trace, and surface only real issues (bugs, unmet criteria, regressions). Use before shipping, after a feature is built, or when the user…
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.