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/d-padmanabhan/agent-engineering-handbook/110-configurationgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/110-configuration)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/110-configuration"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/110-configuration.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 | $0.02325 | $0.02325 |
| Opus 5 | $0.01162 | $0.01162 |
| Sonnet 5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
110-configuration 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 5d 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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configuration Management Engineering Ruleset
Goal: Manage configuration consistently across applications with clear precedence, proper validation, and secure defaults.
Configuration Precedence
Configuration is applied in order, with later sources overriding earlier ones:
- System configuration (
/etc/gitconfig,/etc/app/config.yaml) - User configuration (
~/.gitconfig,~/.app/config.yaml) - Local/project configuration (
.git/config,./config.yaml) - Environment variables (
GIT_AUTHOR_NAME=...,APP_API_KEY=...) - Command-line parameters (
git commit --author=...,app --api-key=...)
This pattern is used by Git, SSH, and many Unix tools. Use this hierarchy to allow:
- System defaults
- User preferences
- Project settings
- Runtime environment overrides
- Explicit command-line overrides
Environment Variables
String Type
Environment variables are strings in the OS. Convert them in your application:
# GOOD: Explicit conversion
port = int(os.getenv("PORT", "8080"))
timeout = float(os.getenv("TIMEOUT", "30.0"))
debug = os.getenv("DEBUG") == "1"
# BAD: Assuming type
port = os.getenv("PORT", 8080) # Wrong! Default should be string
Boolean Values
Use 1 for true. Anything that is not 1 is false.
# GOOD: Consistent boolean handling
debug = os.getenv("DEBUG") == "1"
verbose = os.getenv("VERBOSE") == "1"
enabled = os.getenv("FEATURE_ENABLED") == "1"
# BAD: Parsing various strings
debug = os.getenv("DEBUG", "false").lower() in ["true", "1", "yes", "on"]
# This is brittle and opinionated
Rationale:
- Simple and unambiguous
- Works across all languages
- No parsing ambiguity
- Consistent with Unix conventions
Required Values
Fail fast if required configuration is missing:
# GOOD: Fail fast with clear error
api_key = os.getenv("API_KEY")
if not api_key:
raise ValueError(
"API_KEY environment variable is required. "
"Set it with: export API_KEY=your-key"
)
# BAD: Silent failure or default
api_key = os.getenv("API_KEY", "") # What if empty string?
# Later: api_key is empty, fails mysteriously
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.
- 5d ago First seen · 412 lines · 2,325 tokens per session scan A 996645ff6f45
110-configuration is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 5d ago), licensed MIT. It adds 2,325 tokens to every session, about $0.0116 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
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-assertions-over-defensive-checks
Prefer assertions over defensive checks when data is guaranteed to be valid.
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.