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/golid-ai/golidWrote 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/golid-ai/golid/common-commands)<a href="https://agentmods.dev/rules/golid-ai/golid/common-commands"><img src="https://agentmods.dev/badge/rules/golid-ai/golid/common-commands.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 5.1 | $0.00000 | $0.00681 |
| Opus 5 | $0.00000 | $0.00341 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
common-commands 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 7d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Common Commands
Thesis: Shared commands should be discoverable, copy-safe, and tied to current project scripts so agents do not invent risky shell invocations.
This is an activation rule, not the command catalog. When a task needs a
concrete command for local development, deployment, debugging, GCP, Git,
tests, builds, migrations, or contract validation, read docs/cli-reference.md
and use the project-specific command there instead of inventing an equivalent
shell snippet.
Command Selection Protocol
- Read the catalog first. If the task is nontrivial shell work, check
docs/cli-reference.mdbefore running commands. - Run the known-good command exactly, from the documented directory. Do
not substitute nearby tools (
npxpackage names, alternate test flags, one-off scripts) unless the known command fails. - One failure → diagnose, don't probe. If a known command fails, inspect the concrete error and either fix that cause or report the blocker. Do not try a chain of equivalent commands hoping one works.
- Prefer compile/smoke checks when full commands are unsafe. For example,
compile integration-tagged packages with
go test -tags=integration ... -run '^$'whenTEST_DATABASE_URLis not confirmed safe. - Tell the user what was not run. If a command is skipped because it is destructive, unavailable, or environment-dependent, say so in the closeout.
When to Use
- Starting or debugging local services.
- Running tests, builds, migrations, or seed commands.
- Inspecting GCP logs, secrets, deploy status, or storage.
- Running webhook or external API test commands.
- Checking what needs to be pushed.
- Validating generated contracts such as
backend/openapi.yaml.
Known Command Pitfalls
| Do Not Use | Use Instead | Why |
|---|---|---|
python |
python3 |
The dev container does not provide python; repeated probes waste time. |
grep, find, cat, head, tail |
Cursor tools: rg, Glob, ReadFile |
Tooling rules already provide safer, faster search/read paths. |
npx --yes @apidevtools/swagger-cli ... |
npm run generate:types from frontend/, or a repo-local parser if type generation is too heavy |
npx can fail in Cursor's server path; generated API types are the contract smoke test this repo already uses. |
go test -tags=integration ... without checking env |
Untagged go test, or go test -tags=integration <pkg> -run '^$' for compile-only, unless TEST_DATABASE_URL is confirmed safe |
Integration tests can wipe the dev DB. |
git add -A |
Stage explicit files | Avoid sweeping unrelated user changes into commits. |
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.
- 7d ago First seen · 55 lines · 0 tokens per session scan A 9acd7b40e1a7
common-commands is a cursor rule published in the GitHub repository golid-ai/golid (40 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 681 tokens. 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
adapter-features
Database-specific features must be implemented in the specialized adapter only. Base adapters (postgres, mysql, etc.) must remain database-agnostic.
unit-tests-tdd
TDD required for behavior changes; ≥80% package coverage on touched packages; unit-test conventions.
integration-tests
Human-readable integration test requests; helpers vs httptest; suites/ vs per-DB placement.
state-management
Use the following stack. Do not introduce or recommend Redux or React Context for shared/global state.
backend
You are an expert in Go, Gin, Gorm, Gen, Cosy (https://cosy.uozi.org/) with a deep understanding of best practices and performance optimization techniques in these technologies.
core
Core token-efficiency and response discipline rules. Always active.