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 instructions/vhscom/private-landing/claude-mdgit clone --depth 1 https://github.com/vhscom/private-landingWrote 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/instructions/vhscom/private-landing/claude-md)<a href="https://agentmods.dev/instructions/vhscom/private-landing/claude-md"><img src="https://agentmods.dev/badge/instructions/vhscom/private-landing/claude-md.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 | $0.01808 | $0.01808 |
| Opus 5 | $0.00904 | $0.00904 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
private-landing CLAUDE.md scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
The first agent must be provisioned via direct `curl` against `/ops/agents` — `plctl` requires an existing agent key to start. How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides context for AI assistants working with this codebase.
Project Overview
Private Landing is an educational authentication reference implementation for Cloudflare Workers. It demonstrates secure authentication patterns following NIST SP 800-63B/SP 800-132 guidelines and OWASP recommendations.
Stack: Hono, Turso (libSQL), Valkey (optional), TypeScript, Bun, Zod, Go
Architecture
This is a Bun workspace monorepo with an additional Go tool:
apps/cloudflare-workers/ # Hono app deployed to Cloudflare Workers
packages/core/ # Auth services, middleware, crypto utilities
packages/infrastructure/ # Database client, cache client, static file serving
packages/observability/ # Removable plugin: event capture, adaptive challenges, /ops API + WebSocket
packages/schemas/ # Zod validation schemas
packages/types/ # Shared TypeScript types and error classes
tools/cli/ # plctl — Go TUI for the /ops API (not a Bun workspace)
Key Design Decisions
- JWT dual-token pattern: Short-lived access tokens (15 min) + long-lived refresh tokens (7 days)
- Session linkage: Tokens contain session IDs enabling server-side revocation
- PBKDF2-SHA384: 100,000 iterations with 128-bit salts per NIST SP 800-132
- Timing-safe comparison: Uses
crypto.subtle.verify()for constant-time equality checks - No composition rules: Password policy follows NIST guidance (length only, no complexity requirements)
- Content negotiation: Auth endpoints return JSON when
Accept: application/jsonis sent, redirects otherwise - Optional cache-backed sessions:
CacheClientabstraction (ADR-003) enables Valkey/Redis for session storage viacreateCachedSessionService; SQL remains the default when no cache is configured - Session dual-write:
createMirroredSessionServicedecorator (ADR-007) wraps cache-backed sessions with best-effort SQL writes so operational queries against thesessiontable stay accurate; cache remains authoritative for auth - Password change with full revocation:
POST /account/passwordverifies the current password, updates the hash, and revokes all sessions viaendAllSessionsForUser(ADR-004) - Semantic URL grouping: Routes organized into
/health/*(public probes),/auth/*(authentication lifecycle),/account/*(account management),/ops/*(operational surface) with explicit per-route auth middleware (ADR-005) - Rate limiting: Fixed-window counters via
CacheClient(ADR-006); IP-based keying for public routes, user-based keying for authenticated routes; degrades to no-op when cache is disabled - Observability plugin:
packages/observability(ADR-008) provides structured event emission, adaptive proof-of-work challenges on login, agent credentials, and the/ops/*HTTP surface; removable by deleting the package and commenting two lines inapp.ts - WebSocket gateway:
GET /ops/ws(ADR-009) provides persistent operational connections with authenticate-once upgrade, capability negotiation, heartbeat with credential re-validation, and origin blocking for browser-initiated connections - Cloaking:
/ops/*routes return 404 whenAGENT_PROVISIONING_SECRETis absent, making the surface invisible in default deployments
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.
- 3d ago First seen · 128 lines · 1,808 tokens per session scan A aa67d648fd9f
private-landing CLAUDE.md is an instructions file published in the GitHub repository vhscom/private-landing (79 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,808 tokens to every session, about $0.0090 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vauthenticator AGENTS.md
Instructions for mrFlick72/vauthenticator: This repository is a monorepo with 3 projects.
vauthenticator CLAUDE.md
Instructions for mrFlick72/vauthenticator, a project described as: VAuthenticator OpenID Connect/OAuth2.1 Auth server.
authgear-server AGENTS.md
AGENTS.md instructions for authgear/authgear-server, covering agents.md, repository layout, documentation map, common commands and start local dev.
pi-anthropic-auth AGENTS.md
Instructions for gotgenes/pi-anthropic-auth, covering agents guide: pi-anthropic-auth, project, primary goal, current status and principles.
claude-mesh CLAUDE.md
Instructions for pouriamrt/claude-mesh, covering claude.md, what this is, commands, scope to one package and l3 end-to-end against a real claude binary.
WealthWise-Finance-Tracker CLAUDE.md
Instructions for hoangsonww/WealthWise-Finance-Tracker, covering claude.md - wealthwise, project overview, quick reference, package names and file conventions.