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/qwickapps/ai-sdlc-workflows/iteration-gatesgit clone --depth 1 https://github.com/qwickapps/ai-sdlc-workflowsWhat 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 | $0.01620 | $0.01620 |
| Opus 5 | $0.00810 | $0.00810 |
| Sonnet 5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
ITERATION-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 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 — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iteration Gates
When to apply: During spike investigations, feature development, and any task requiring iteration to reach satisfactory quality.
Core Principle
Loop back to improve incomplete or shallow work. Do not proceed with unsatisfactory output.
Iteration is expected. First attempts are often incomplete. The goal is satisfactory work, not fast work.
Reference: See COMMON-PATTERNS.md for gate decision logic and SATISFACTORY-CRITERIA.md for quality standards.
When to Iterate (Loop Back)
Completeness Gate
Iterate if ANY true:
- Items not individually investigated ("X plugins may need attention")
- Claims lack specific evidence (file:line, URLs)
- "Unknown" items don't explain WHY unknowable
- Vague placeholder language ("may need", "possibly", "approximately")
- Critical dependencies grouped not assessed individually
- Investigation methods available but not attempted
Action: Return to investigation, address gaps, re-check gate.
Evidence Gate
Iterate if ANY true:
- Claims without sources
- File refs without line numbers
- Code behavior without verification
- Compatibility claims without checking requirements
- "Should work" without evidence
- Assumptions presented as facts
Action: Gather evidence, document sources, re-check gate.
Reference: See FACT-VERIFICATION.md for verification standards.
Depth Gate
Iterate if ANY true:
- Only checked public sources (didn't check local)
- Read file names not contents
- Listed packages didn't inspect configuration
- Found plugin name didn't check implementation
- Saw error didn't trace root cause
- Shallow investigation for critical areas
Action: Deeper investigation, read code, trace paths, re-check gate.
Reference: See RESEARCH-DEPTH.md for depth levels and INVESTIGATION-METHODS.md for method hierarchy.
When to Proceed (Don't Iterate)
Proceed if ALL true:
- All items individually investigated or gaps documented with reason
- All claims have specific evidence (file:line or URL)
- All "unknown" items explain WHY unknowable and what's needed
- No vague language - all statements specific
- Critical areas deeply investigated (code inspection)
- All available methods attempted or documented why not
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 · 268 lines · 1,620 tokens per session scan A aaabacc1da0b
ITERATION-GATES is a cursor rule published in the GitHub repository qwickapps/ai-sdlc-workflows (2 stars, last pushed 5mo ago), licensed MIT. It adds 1,620 tokens to every session, about $0.0081 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 2026-08-31.
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-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.
family-instance-domain-actions
Family instance domain action implementation patterns.