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/kanevry/session-orchestrator/020-quality-gatesgit clone --depth 1 https://github.com/Kanevry/session-orchestratorWrote 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/kanevry/session-orchestrator/020-quality-gates)<a href="https://agentmods.dev/rules/kanevry/session-orchestrator/020-quality-gates"><img src="https://agentmods.dev/badge/rules/kanevry/session-orchestrator/020-quality-gates.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 | $0.00017 | $0.00938 |
| Opus 5 | $0.00009 | $0.00469 |
| Sonnet 5 | $0.00003 | $0.00188 |
| Haiku 4.5 | $0.00002 | $0.00094 |
Grade A, and why
020-quality-gates 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 6d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quality Gates
Four quality gate variants for different session phases. Commands are read from Session Config in CLAUDE.md (field defaults shown below).
Config Fields
| Field | Default | Notes |
|---|---|---|
test-command |
pnpm test --run |
Set to skip to disable |
typecheck-command |
tsgo --noEmit |
Set to skip to disable |
lint-command |
pnpm lint |
Set to skip to disable |
Variant 1: Baseline
When: Session start (Phase 3) Purpose: Quick health check — non-blocking.
{typecheck-command} 2>&1 | tail -5
{test-command} 2>&1 | tail -5
- Report results but do NOT block the session
- Store error counts as the session baseline for later comparison
Variant 2: Incremental
When: After implementation waves (Impl-Core, Impl-Polish) Purpose: Verify implementation did not break anything.
# Run tests on changed files only
{test-command} -- <changed-test-files>
# Full typecheck (always full — partial typecheck is unreliable)
{typecheck-command}
- Report failures but do NOT block wave progression
- If issues found, add fix tasks to the next wave automatically
Variant 3: Full Gate
When: Session end (Phase 2) — before committing Purpose: Final quality gate — BLOCKING.
# 1. Typecheck — must produce 0 errors
{typecheck-command}
# 2. Tests — must pass (exit code 0)
{test-command}
# 3. Lint — errors NOT OK, warnings OK
{lint-command}
# 4. Debug artifact scan
grep -rn 'console\.log\|debugger\|TODO: remove' \
--include='*.ts' --include='*.tsx' --include='*.js' \
src/ lib/ 2>/dev/null || true
Rules:
- Do NOT commit if any check fails
- Fix quick issues (<2 min) inline
- For longer fixes: create a
priority::highissue and exclude affected files from commit
Variant 4: Per-File
When: Session review (reviewer agent) Purpose: Targeted check on specific changed files.
# Run tests for specific files
{test-command} -- <specific-file-paths>
# Full typecheck
{typecheck-command}
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.
- 6d ago First seen · 129 lines · 17 tokens per session scan A 2a9cb7e91c21
020-quality-gates is a cursor rule published in the GitHub repository Kanevry/session-orchestrator (49 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 938 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
context-discipline
Manage AI context window efficiently - read before write, no re-reads, tool-call budgets, one-pass discipline.
kandev-pr-fixup
Kandev PR fixup workflow prompt for Cursor agents.
cursor-tools-mastery
Cursor 3.7 runtime guide: choose the right tool, canvases, Design Mode, /worktree, /best-of-n, Await, and parallel execution where safe.
conventional-commits
Always use Conventional Commits for git commit messages.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.