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/alphabitcore/nexus-gateway/code-doc-lockstepgit clone --depth 1 https://github.com/AlphaBitCore/nexus-gatewayWhat 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 | $0.01054 | $0.01054 |
| Opus 5 | $0.00527 | $0.00527 |
| Sonnet 5 | $0.00211 | $0.00211 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
code-doc-lockstep 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code / Doc Lockstep (BINDING)
Docs are the single source of truth. If code drifts from a doc, the code is wrong — fix the doc to match reality if needed, but never ship code that contradicts its doc.
The rule
When a PR touches code in a region covered by a doc, every matching doc MUST be updated in the same commit. The doc isn't a follow-up; it's part of the change. This applies to every doc tree:
| Doc tree | What changes here trigger an update |
|---|---|
docs/developers/architecture/** |
internal mechanics, data flow, contracts between services |
docs/users/features/** |
user-visible UI surface, admin features, agent UX |
docs/users/api/openapi/** |
request/response schemas, new/renamed/removed endpoints |
docs/operators/ops/runbooks/** |
deployment steps, recompute scripts, operational procedures |
docs/developers/specs/** |
Epic / Story acceptance criteria as scope evolves |
A single code change typically touches multiple doc trees. Examples:
- New admin endpoint → OpenAPI spec + architecture doc + feature doc (if UI surface) + runbook (if ops procedure).
- Cost-stamping change →
cost-estimation-architecture.md+prod-deploy-data-changes.md(if historical recompute) + feature doc for the Traffic drawer (if visible breakdown changes). - Provider adapter codec change →
provider-adapter-architecture.md+ feature doc if visible to admins. - Schema migration →
cost-estimation-architecture.md(if cost columns) ORthing-config-sync-architecture.md(if shadow) + runbook if any historical data fix is part of the PR.
How it's enforced
scripts/check-doc-lockstep.mjs runs on the PR diff against origin/main. If any code file matches a configured glob and none of the mapped docs are in the diff, the check fails with the file list + which docs were expected.
The mapping lives at scripts/doc-lockstep.config.mjs. Each entry is one or more code globs plus one or more required docs. Adding a new entry is easy — edit the config and open the PR.
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 · 69 lines · 1,054 tokens per session scan A a1f2aa85cd5e
code-doc-lockstep is a cursor rule published in the GitHub repository AlphaBitCore/nexus-gateway (22 stars, last pushed 6d ago), licensed Apache-2.0. It adds 1,054 tokens to every session, about $0.0053 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 2026-08-30.
Other cursor rules, from other repositories
10-deterministic-audit
Enforce deterministic audit behavior — no invented controls, cite authoritative sources, emit traceable artifacts.
flagship_author
How to author a flagship in ks-cookbook.
recipe_author
How to author a recipe in ks-cookbook.
30-framework-routing
Route tasks to HIPAA, HITECH, PCI-DSS, SOC 2, ISO 27001, NIST CSF, NIST AI RMF, FERPA, COPPA, CCPA, US state privacy, GDPR, FedRAMP, SOX, CMMC, and GLBA skills based on user intent and presets.
00-compliance-agent-core
Core compliance agent mission, PHI redaction gate, and audit lifecycle for HIPAA, PCI-DSS, and SOC 2.
20-phi-redaction-first
PHI redaction first — Presidio gate, token handling, and minimum necessary LLM access for HIPAA workflows.