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/renanflustosa/octo-clusterWrote 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/renanflustosa/octo-cluster/00-consumer-boundary)<a href="https://agentmods.dev/rules/renanflustosa/octo-cluster/00-consumer-boundary"><img src="https://agentmods.dev/badge/rules/renanflustosa/octo-cluster/00-consumer-boundary/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/renanflustosa/octo-cluster/00-consumer-boundary"><img src="https://agentmods.dev/badge/rules/renanflustosa/octo-cluster/00-consumer-boundary.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 | $0.00364 | $0.00364 |
| Opus 5 | $0.00182 | $0.00182 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
00-consumer-boundary 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 today.
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
Master rule — consumer boundary (public framework)
Consumer identifiers are treated as secrets.
Any consumer-specific name, repository name, workspace name, project name, product name, company name, acronym, codename, or internal reference must be handled with the same severity as a credential leak.
Public repositories must never store them.
Applies to every git change in octo-cluster
Before staging, committing, pushing, or opening a PR in this repository:
- Generalize consumer-specific names in tracked paths and file contents — or remove them.
- Relocate consumer context to a gitignored local overlay or a separate consumer workspace — never the public tree.
- Run
.\scripts\boundary-audit.ps1 -Stagedbefore commit; full.\scripts\boundary-audit.ps1before push. Configure patterns inboundary-patterns.local.yaml(seeboundary-patterns.example.yaml). - Stop if the audit fails — fix violations before proceeding. Do not bypass hooks, CI, or this rule.
In scope
Filenames, folder names, markdown, yaml, json, prompts, scripts, commit messages, PR titles and bodies, and comments in tracked files.
Do not
- Add real client, product, repo, vault, or workspace names to tracked source.
- Copy private overlay paths or consumer vocabulary into public docs, examples, or tests.
- Commit until
boundary-auditpasses on staged changes.
Reference
scripts/boundary-audit.ps1 · .githooks/pre-commit · .githooks/pre-push
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.
- today Changed · +20 tokens per session 8159dd0b4a37
- 10d ago First seen · 36 lines · 344 tokens per session scan A 547c41e1e23a
00-consumer-boundary is a cursor rule published in the GitHub repository renanflustosa/octo-cluster (4 stars, last pushed yesterday), licensed MIT. It adds 364 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
nauro-adopt
Seeds Nauro's project store from an existing repo. Use after nauro adopt has run locally. On filesystem-capable surfaces, reads docs (README, manifests, ADRs, Memory-Bank) for rationale and inspects code, config, tests, lockfiles, and recent git history for evidence, then surfaces targeted probes that turn evidence…
nauro-context
Writes durable shared context into Nauro's project store so other agents (a later session or a parallel one) can discover and pull it, finds and reads context another agent left, or captures a resumable brief so your own next session in this environment picks up cleanly. Three modes. Author writes a shared brief for…
nauro-interview
Ask compact, numbered prerequisite-ready questions to elicit tacit project reasoning or challenge a proposed choice against Nauro decisions and repository evidence. Continue until every material branch has a disposition, then classify the result as shared understanding without granting write authority. Use only when…
nauro-loop
Originate gated Delivery and Interview candidates, or coordinate selected Program Delivery as FRAME -> CHOOSE -> START -> ADVISE -> VERIFY -> ADVANCE. Human-named work bypasses candidate selection. Agent-originated work keeps read-only ORIENT, 1-3 candidates, mandatory human selection, reject-all, and no auto-pick…
nauro-ship-task
Run the full planner -> executor -> reviewer -> tech-lead -> direct-user-confirm -> push chain through Cursor's native project workflow agents. Requires the four bundled .cursor/agents/nauro-.md definitions and fails closed without native dispatch.
scout
Reveal consequential blind spots after answering.