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/kaademos/secure-sdlc-agents/secure-sdlcgit clone --depth 1 https://github.com/Kaademos/secure-sdlc-agentsWhat 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 | $0.01018 | $0.01018 |
| Opus 5 | $0.00509 | $0.00509 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade B, and why
secure-sdlc scanned grade B with 1 finding 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- **Prompt injection** — can user input override system instructions? Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure SDLC — Active Security Context
You are operating with a Secure SDLC agent team available via MCP tools (sdlc_*).
Apply security thinking at every step. Do not wait to be asked.
When writing or reviewing code, automatically check:
Authentication & Session
- Every API route / endpoint has authentication enforced — no auth bypass paths
- Session tokens are cryptographically random (≥128 bits) and invalidated on logout
- Passwords stored with bcrypt (cost ≥12), Argon2id, or scrypt — never MD5/SHA alone
- JWT tokens have
algvalidated explicitly — never acceptalg: none
Authorisation
- Every object access checks the requesting user OWNS or has permission for that SPECIFIC resource (prevent IDOR)
- Default deny: if no rule grants access, deny
- Server-side auth on every request — never trust client-supplied role claims
Input Handling
- All inputs validated server-side (allowlist, not denylist)
- Queries use parameterised statements / ORM — no string concatenation with user input
- File uploads: validate by magic bytes (not MIME/extension), reject SVG, randomise stored filenames
- Never use user input directly in filesystem paths, shell commands, or eval
Secrets & Cryptography
- No secrets in code, config files, or environment files committed to git
- AES-256-GCM or ChaCha20-Poly1305 for encryption at rest
- TLS 1.2 minimum for all communications; TLS 1.3 preferred
- Keys live in secrets managers (Vault, AWS SM, etc.) — never hardcoded
Error Handling & Logging
- Generic error messages to users; detailed errors logged server-side
- Never log credentials, tokens, PII, or payment data
- Log: auth attempts, access control decisions, admin actions (timestamp, user, IP, outcome)
Dependencies
- New packages reviewed before adding: check CVE status, maintenance, download count
- SCA (Software Composition Analysis) on every PR
MCP Tool Triggers — invoke automatically when these situations occur:
| Situation | Tool to invoke |
|---|---|
| Starting a new feature | sdlc_plan_feature |
| Designing architecture | sdlc_threat_model |
| Reviewing a PR or code diff | sdlc_review_pr |
| Writing/reviewing Terraform, K8s, Helm | sdlc_review_infra |
| SAST tool produced findings | sdlc_triage_sast |
| About to deploy / release | sdlc_release_gate |
| Building AI/LLM features | sdlc_ai_security_review |
| Quick security question | sdlc_security_champion |
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 · 99 lines · 1,018 tokens per session scan B 4125a446328f
secure-sdlc is a cursor rule published in the GitHub repository Kaademos/secure-sdlc-agents (13 stars, last pushed 1mo ago), licensed MIT. It adds 1,018 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). 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
aggregatereports to keep SUMMARY.md and metadata.json synchronized.
cursor
CodeInspectus — scan, surface findings, fix only with user consent.
ai-safe2-sovereign
AI SAFE2 v3.0 Sovereign Security Rules for Cursor.
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.