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/homenshum/nodebenchai/agentic_reliabilitygit clone --depth 1 https://github.com/HomenShum/NodeBenchAIWhat 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 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
agentic_reliability scanned grade A with 1 finding 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `fetch(variable)` without URL validation What it actually says
Agentic Systems Reliability
Every tool response must be honest, every resource bounded, every failure surfaced. Agents trust tool output literally.
8-Point Mandatory Checklist (run on ALL backend/infra code)
- BOUND — Every in-memory collection (Map, Array, Set) has MAX + eviction on insert
- HONEST_STATUS — No 2xx on failure paths. 502 for backend down, 504 for timeout, 500 for unhandled
- HONEST_SCORES — No hardcoded
passed: trueor score floors. Defaultfalse/0/"UNKNOWN"when not evaluated - TIMEOUT — AbortController + checkBudget() gates between async stages. Return 504 on expiry
- SSRF — URL validation (protocol + hostname blocklist) before every fetch with agent/user input
- BOUND_READ — ReadableStream with MAX_BYTES + cancel on overflow for all external response bodies
- ERROR_BOUNDARY — asyncHandler wrapper or try/catch on every async route handler
- DETERMINISTIC — stableStringify (sorted keys) for all content-addressed hashing
Why Agents Amplify Bugs
- Agents call tools in tight loops → unbounded Maps OOM in minutes not hours
- Agents parse status codes literally → fake 201 becomes false belief in reasoning chain
- Agents generate URLs from reasoning → SSRF via hallucinated internal addresses
- Inflated evidence scores → agents skip verification on bad data
Severity
- P0: Crash, SSRF, false decisions from fake data → fix immediately
- P1: Degraded data, no crash → fix same session
- P2: Suboptimal but safe → fix when touched
What to Grep For
new Map()without MAX constant in same fileres.status(2in catch/fallback branchespassed: truewith "caller should validate" commentsawait response.text()on external fetchesfetch(variable)without URL validationasync (req, res) =>without error handlingJSON.stringify(obj)→createHashwithout sorted keys
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.
- 2d ago First seen · 41 lines · 513 tokens per session scan A c35cee59d916
agentic_reliability is a cursor rule published in the GitHub repository HomenShum/NodeBenchAI (14 stars, last pushed 18d ago), licensed MIT. It adds 513 tokens to every session, about $0.0026 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
java-springboot-jpa-cursorrules-prompt-file
description: "Cursor rules for Java development with Springboot and JPA integration." globs: / alwaysApply: false.
conservative-file-creation
Check for existing files before creating. Be conservative about new files and code.
secure-dev-rust
These rules apply to all Rust code in the repository and aim to prevent common security risks through disciplined use of memory safety, input validation, error handling, and safe APIs.
design-patterns
Design patterns (GoF) and file size conventions for sweagent TypeScript codebase.
cursorrules
ALWAYS start your session by reading AGENTS.md and .memory/wiki/hot.md to get project context before suggesting code or answering questions.