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/golid-ai/golid/audit-codebasegit clone --depth 1 https://github.com/golid-ai/golidWhat 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 | $0.00021 | $0.02046 |
| Opus 5 | $0.00010 | $0.01023 |
| Sonnet 5 | $0.00004 | $0.00409 |
| Haiku 4.5 | $0.00002 | $0.00205 |
Grade A, and why
audit-codebase 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 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.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Audit Checklist
Thesis: Score the codebase across 7 categories with exact file citations. Check ADRs before flagging documented design decisions.
Run this checklist for release readiness audits. Cite exact file paths and line numbers for every finding. Check docs/adr/ for ADRs before flagging documented design decisions.
Core patterns (apperror, parameterized SQL, batch(), Switch/Match, createResource, alive guard) — see codebase-standards. Frontend fetch — solidjs-data-fetching. Route UI — solidjs-pages.
Backend
- All SQL uses $N parameterized placeholders (no fmt.Sprintf with values or identifiers)
- No
_ = fn()discarded errors in production code - No
echo.NewHTTPErrorin production code (use apperror) - Token refresh is transactional and TOCTOU-safe (atomic UPDATE...RETURNING)
- Password reset uses SELECT...FOR UPDATE inside transaction
- Verification tokens hashed with selector/verifier pattern
- All
rows.Next()loops checkrows.Err()after iteration - JWT_SECRET rejects CHANGE_ME placeholder at startup
- Production entrypoint exits on migration failure
- Timeout middleware uses Echo's built-in (no custom goroutine race)
- All operational constants in Config struct with env var overrides
- ForgotPassword/ResendVerification log errors server-side (anti-enumeration: always return 200)
Frontend
- Zero
createResource— use onMount + signals (seesolidjs-data-fetching) - Zero nested
<Show>for content states — useSwitch/Match(seesolidjs-pages) - Zero
window.confirm()— useDestructiveModal(seesolidjs-pages) - Zero onMount/createEffect cleanup returns — use
onCleanup(seesolidjs-data-fetching) - Zero
anyin production — useunknown(e.g.Record<string, unknown>) - Auth store reacts to
auth:session-expiredwhen token cleared - Auth cookie
Secureon HTTPS set and clear paths - Skip link present with correct target and
tabindex - Auth guard effects use
on()without defer (seesolidjs-pages) -
batch()wraps signal updates after everyawait(seesolidjs-data-fetching)
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 · 136 lines · 21 tokens per session scan A 7393475c1b60
audit-codebase is a cursor rule published in the GitHub repository golid-ai/golid (40 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 2,046 once invoked, about $0.0001 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
cursorrules
AGENTS.md.
adapter-features
Database-specific features must be implemented in the specialized adapter only. Base adapters (postgres, mysql, etc.) must remain database-agnostic.
git-commits
Git commit safety — commits are human-only; AI suggests, never executes.
unit-tests-tdd
TDD required for behavior changes; ≥80% package coverage on touched packages; unit-test conventions.
token-optimization
Agent-mode tool-call efficiency. Cuts the largest hidden cost in modern AI IDEs — wasted tool calls and oversized context windows.
config-resilience
Config warn-and-continue for non-sensitive keys; Auth/ACL/JWT/secrets/DB credentials fail closed.