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.
git clone --depth 1 https://github.com/bordenet/golden-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/rules/bordenet/golden-agents/invariants)<a href="https://agentmods.dev/rules/bordenet/golden-agents/invariants"><img src="https://agentmods.dev/badge/rules/bordenet/golden-agents/invariants/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/rules/bordenet/golden-agents/invariants"><img src="https://agentmods.dev/badge/rules/bordenet/golden-agents/invariants.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00373 | $0.00373 |
| Opus 5.5 | $0.00149 | $0.00149 |
| Sonnet 5.5 | $0.00075 | $0.00075 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
invariants 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 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.
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.
What it actually says
Critical Invariants — Always Follow
Load at START of every conversation.
Self-Management Protocol
After editing ANY guidance file, run: wc -l AGENTS.md .ai-guidance/*.md 2>/dev/null
| File | Limit | Action if exceeded |
|---|---|---|
AGENTS.md |
250 lines | Extract to .ai-guidance/*.md |
.ai-guidance/*.md |
250 lines | Split into sub-directory |
If threshold exceeded: STOP → draft a diff for a human to merge. Do not apply the diff. The size cap exists so agents do not grow the file they are reading.
Zero Data Loss Checklist
- Snapshot captured:
cat <file> > /tmp/original.md - Every section accounted for in new structure
- No rules deleted (only moved/split)
- Diff shows reorganization, not deletion
Refactoring Steps
AGENTS.md → .ai-guidance/:
- Snapshot →
mkdir -p .ai-guidance→ Classify by topic - Extract to sub-files (≤250 lines each) → Update loading table
- Verify:
wc -l AGENTS.md≤250
Sub-file → sub-directory (e.g., testing.md exceeds 250 lines):
mkdir -p .ai-guidance/testing- Split into topic files (
unit.md,integration.md, etc.) - Replace original with index referencing sub-files
- Verify: each file ≤250 lines
Recovery: If verification fails, restore from /tmp/original.md
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.
- 5d ago First seen · 45 lines · 373 tokens per session scan A 574c3b2e6717
invariants is a cursor rule published in the GitHub repository bordenet/golden-agents (2 stars, last pushed 3d ago), licensed MIT. It adds 373 tokens to every session, about $0.0015 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 2026-11-12.
invariants compared with cursor rules from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| invariantsbordenet/golden-agents | Cursor rule | 2 | 3d ago | MIT | A | 373 | Cursor |
| ponytailDietrichGebert/ponytail | Cursor rule | 192k | 18d ago | MIT | A | 604 | Cursor |
| angular-20angular/angular | Cursor rule | 101k | today | MIT | A | 0 | Cursor |
| dev-standardapache/superset | Cursor rule | 76k | today | Apache-2.0 | A | 1,147 | Cursor |
| prefer-assertions-over-defensive-checksprisma/orm | Cursor rule | 48k | today | Apache-2.0 | A | 0 | Cursor |
| prefer-direct-imports-over-module-mocksprisma/orm | Cursor rule | 48k | today | Apache-2.0 | A | 0 | Cursor |
| as-contract-cast-smellprisma/orm | Cursor rule | 48k | today | Apache-2.0 | A | 943 | Cursor |