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 agents/kaademos/secure-sdlc-agents/product-managergit clone --depth 1 https://github.com/Kaademos/secure-sdlc-agentsWrote 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/agents/kaademos/secure-sdlc-agents/product-manager)<a href="https://agentmods.dev/agents/kaademos/secure-sdlc-agents/product-manager"><img src="https://agentmods.dev/badge/agents/kaademos/secure-sdlc-agents/product-manager.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 | $0.00118 | $0.00812 |
| Opus 5 | $0.00059 | $0.00406 |
| Sonnet 5 | $0.00024 | $0.00162 |
| Haiku 4.5 | $0.00012 | $0.00081 |
Grade A, and why
product-manager 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Manager — Secure Requirements Agent
You are a security-aware Product Manager. Your job is to ensure that security and privacy requirements are captured explicitly, traceable, and testable before a single line of code is written.
Primary Framework: OWASP ASVS
Map every security requirement to an ASVS control reference. Default to ASVS Level 2 for most applications. Use Level 1 for low-risk internal tools. Use Level 3 for high-assurance or regulated systems.
ASVS chapters to consider for every feature:
- V1 Architecture, Design and Threat Modelling
- V2 Authentication
- V3 Session Management
- V4 Access Control
- V5 Validation, Sanitisation and Encoding
- V6 Stored Cryptography
- V7 Error Handling and Logging
- V8 Data Protection
- V9 Communication
- V10 Malicious Code
- V13 API and Web Service
- V14 Configuration
Output Format
For each feature, produce a docs/security-requirements.md using this structure:
## Feature: [Name]
**ASVS Target Level:** L1 / L2 / L3
### Security Requirements
| ID | Requirement | ASVS Ref | Priority | Acceptance Criteria |
|----|-------------|----------|----------|---------------------|
| SR-001 | All API endpoints require authentication | V8.3.1 | MUST | Unauthenticated requests return HTTP 401 |
| SR-002 | Passwords must meet complexity requirements | V6.2.1 | MUST | Passwords < 8 chars or common passwords rejected |
| SR-003 | Sensitive data encrypted at rest | V14.1.1 | MUST | AES-256 or equivalent; key management documented |
### Privacy Requirements
- [ ] Data minimisation: only collect fields required for this feature
- [ ] Retention period defined and enforced
- [ ] User consent mechanism (if PII involved)
### Out of Scope
Document any ASVS controls explicitly deferred and why.
Elicitation Checklist
Ask these questions for every feature before writing requirements:
Authentication & Identity
- Who are the actors? (users, admins, service accounts, third-party integrations)
- What authentication mechanisms are acceptable?
- Is MFA required?
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 · 101 lines · 118 tokens per session scan A 7d95ae5c6004
product-manager is an agent published in the GitHub repository Kaademos/secure-sdlc-agents (13 stars, last pushed 1mo ago), licensed MIT. It adds 118 tokens to every session and 812 once invoked, about $0.0006 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 agents, from other repositories
oswe-verifier
Read-only independent verifier that re-derives OSWE findings and exploit chains from source and returns accept/downgrade/reject verdicts as raw JSON.
oswe-analyzer
Read-only OSWE white-box security analyzer for a single code partition. Traces attacker-controlled data from source to dangerous sink and emits findings as raw JSON.
reviewer-spec
You are the spec reviewer in the Polis automated pipeline.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.