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 agentmods add instructions/kuzivaai/getregula/agents-mdgit clone --depth 1 https://github.com/kuzivaai/getregulaWrote 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/instructions/kuzivaai/getregula/agents-md)<a href="https://agentmods.dev/instructions/kuzivaai/getregula/agents-md"><img src="https://agentmods.dev/badge/instructions/kuzivaai/getregula/agents-md.svg" alt="Measured on agentmods" 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 | $0.00915 | $0.00915 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
getregula AGENTS.md 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 4d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Regula — Agent Instructions
Start with docs/ENGINEERING_ROADMAP.md, then verify mutable GitHub, deployment and
registry observations directly. Public repository content must be limited to
product code, reusable engineering evidence and user-facing documentation.
EU AI Act compliance CLI for code. Python 3.10+ stdlib-only core.
GitHub: kuzivaai/getregula | Distribution: source-only while PyPI is unavailable | CLI: regula
Build & Test
# Verify (run all before claiming done)
python3 tests/test_classification.py && python3 -m pytest tests/ -q && python3 -m scripts.cli self-test && python3 -m scripts.cli doctor
Key Constraints
- IMPORTANT: Bare imports only:
from errors import RegulaError, NOTfrom scripts.errorsor.errors. Everyscripts/*.pyfile usessys.path.insert(0, str(Path(__file__).parent))at the top. Do NOT remove or convert to relative imports. - Zero external dependencies: stdlib-only core, do not add packages
- Do not refactor cli.py monolith unless explicitly asked
- Do not change
json_output()envelope format:{format_version, regula_version, command, timestamp, exit_code, data} - Do not delete manual test list at bottom of
tests/test_classification.py - Locale sync: changes to EN site content must also update DE and PT-BR versions
- Regulatory claims: cite specific article numbers; include Omnibus caveat for EU AI Act deadlines; see
regulatory-contextskill for current status - Privacy-guard awareness: repository operations are scanned for credential and private-data patterns. Use char-code construction for sensitive-shape test fixtures.
- Public-repository privacy: never commit handovers, session logs, private
plans, pricing experiments, outreach records, personal names or contact
details, immigration/employment context, local usernames, hostnames or
machine-specific absolute paths. Use
/home/USER,/mnt/c/Users/USERandLOCAL-MACHINEin public examples.
Quality Checkpoints
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.
- 4d ago First seen · 52 lines · 915 tokens per session scan A b9cde72ca373
getregula AGENTS.md is an instructions file published in the GitHub repository kuzivaai/getregula (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 915 tokens to every session, about $0.0046 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
permit0 CLAUDE.md
Instructions for permit0-ai/permit0, covering claude.md, commands, build, test (ci uses nextest) and run a single test.
agent-governance-toolkit copilot-instructions.md
Copilot instructions for microsoft/agent-governance-toolkit, covering copilot instructions for agent-governance-toolkit, architecture, build, test, and lint, python and install (editable, all extras).
agent-governance-toolkit AGENTS.md
AGENTS.md instructions for microsoft/agent-governance-toolkit, covering agent governance toolkit - repository instructions, project overview, repository layout status, where changes belong and routing rules.
AgentGuard AGENTS.md
AGENTS.md instructions for WhitzardAgent/AgentGuard, covering agents.md, project summary, repository layout, setup and build / test / lint commands.
agile_v_skills AGENTS.md
AGENTS.md instructions for Agile-V/agile_v_skills, covering agents.md — agile v skills library, repository context, project overview, repository structure and build / lint / test commands.
agile_v_skills CLAUDE.md
Claude Code instructions for Agile-V/agile_v_skills, covering agile v for claude code, install the plugin, choose a profile, shared rules and verify.