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 commands/justdvp/claude-code-templates/middlewaregit clone --depth 1 https://github.com/Justdvp/claude-code-templatesWhat 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 | $0.00000 | $0.00572 |
| Opus 5 | $0.00000 | $0.00286 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
middleware 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- middleware — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Express Middleware
Create Express middleware for $ARGUMENTS following project conventions.
Task
Create or optimize Express middleware based on the requirements:
- Analyze existing middleware: Check current middleware patterns, naming conventions, and file organization
- Examine Express setup: Review app configuration, middleware stack order, and TypeScript usage
- Identify middleware type: Determine the middleware category:
- Authentication/Authorization (JWT, sessions, role-based)
- Validation (request body, params, query validation)
- Logging (request/response logging, audit trails)
- Error handling (global error handlers, custom errors)
- Security (CORS, rate limiting, helmet)
- Utility (parsing, compression, static files)
- Check dependencies: Review existing middleware dependencies to avoid duplication
- Implement middleware: Create middleware with proper TypeScript types and error handling
- Test middleware: Write unit and integration tests following project patterns
- Update middleware stack: Integrate middleware into Express app configuration
- Add documentation: Include JSDoc comments and usage examples
Implementation Requirements
- Follow project's TypeScript conventions and interfaces
- Use existing error handling patterns and response formats
- Include proper request/response typing with custom interfaces
- Add comprehensive error handling and logging
- Consider middleware execution order and dependencies
- Implement proper async/await patterns for async middleware
- Follow project's folder structure for middleware files
Middleware Patterns to Consider
Based on the request:
- Authentication: JWT verification, session management, API key validation
- Authorization: Role-based access control, permission checking
- Validation: Schema validation with Joi/Zod, sanitization
- Logging: Request logging, performance monitoring, audit trails
- Error Handling: Global error handlers, custom error classes
- Security: CORS configuration, rate limiting, input sanitization
- Utility: Request parsing, response formatting, caching
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 · 61 lines · 0 tokens per session scan A 2a7b7a3daaa4
middleware is a command published in the GitHub repository Justdvp/claude-code-templates (7 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 572 tokens. 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 commands, from other repositories
audit-steps
Audit one or all pipelines against layout, frontmatter, topology, and runtime-safety standards — produces a severity-classified report (SEV-0/1/2/3) with cited evidence.
init-deep
Initiates a repository traversal to create localized PIPELINE-CONTEXT.md hierarchical context files.
migrate-pipeline
Migrate an existing pre-v2 per-tier pipeline (.claude/, .opencode/, .agents/codex/) into the unified data-only .superpipelines/ layout — select legacy pipeline, translate frontmatter to canonical agent defs, stage, delta-audit, gate on human approval, then atomically promote, rewrite the registry, and move the legacy…
delete-step
Delete a step from an existing pipeline — select pipeline, select step, perform gap analysis, optionally rewire, audit the delta, then gate on human approval before any deletion.
new-pipeline
Design and scaffold a new named multi-agent pipeline with git preflight, scope selection, pre-gate audit, and entry-skill generation.
new-step
Add a new step to an existing pipeline — select pipeline, choose insertion point, design component, audit the delta, then gate on human approval.