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 rules/ocentra/ocentra-enforcer/ingest_reference_specgit clone --depth 1 https://github.com/ocentra/ocentra-enforcerWhat 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 | $0.00367 | $0.00367 |
| Opus 5 | $0.00183 | $0.00183 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
ingest_reference_spec 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 yesterday.
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
Reference money-critical & security-testing spec (ingest fixture)
Neutral fixture form of the ingested reference spec
(docs/plans/enforcer-selfhost-plan/refs/security-testing-source.md) §2.3
invariants and §3.1-3.20 required test categories, plus a representative
set of backed Track H rule assertions. No product/company/game branding.
Required test categories
- auth-authz
- cors-origin
- input-validation-schema
- url-path-manipulation
- replay-idempotency
- partial-failure-exploitation
- state-logic-abuse
- ddos-resource-exhaustion
- solana-blockchain-abuse
- request-smuggling-protocol
- api-websocket
- error-handling-info-leak
- key-signing
- time-clock-drift
- economic-exhaustion
- rollback-recovery-abuse
- cross-component-trust
- serialization-encoding
- kill-switch-circuit-breaker
- test-integrity-meta
Invariants
- idempotent-replay
- failure-not-reward
- retry-not-mutation
- partial-failure-not-profit
- order-not-advantage
- attacker-cost-not-below-system-cost
- compensation-idempotent-replay-safe
- time-assumptions-fail-closed
- backend-never-signs-unverifiable
- emergency-reduces-blast
Rules
- MCM-SIGNING.1 (T1)
- MCM-TIME.1 (T1)
- MCM-BOUNDARY.1 (T1)
- MCM-KILLSWITCH.1 (T1)
- MCM-ECONOMIC.1 (T2)
- MCM-ROLLBACK.1 (T2)
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.
- yesterday First seen · 52 lines · 367 tokens per session scan A 89708bc29646
ingest_reference_spec is a cursor rule published in the GitHub repository ocentra/ocentra-enforcer (0 stars, last pushed 6d ago), licensed MIT. It adds 367 tokens to every session, about $0.0018 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 cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.