agentmods.dev

silentfail: Instructions file for Claude Code

CLAUDE.md

silentfail CLAUDE.md is an instructions file for Claude Code from decksaga/silentfail. It costs 456 tokens per session, scanned A, original, MIT.

Repository-specific instructions for Claude Code when working on SilentFail, a diagnostic tool for MCP servers. They describe its commands, code structure, operating modes, and important files.

In plain words
What is it for?
Working on SilentFail’s build, command-line options, MCP tools, server discovery, tool testing, security scanning, and web dashboard.
Why use it?
They give the coding assistant the context needed to change or troubleshoot SilentFail correctly. The instructions explain how its command-line tool, MCP server, scanner, security checks, and dashboard fit together.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is decksaga/silentfail's own configuration. It tells Claude Code how to work on silentfail itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything silentfail configures →

not rated 1repo 5mo ago A scan 456 tokens original MIT
View source ↗ decksaga/silentfail
Reuse

Borrowing it

Nothing to install: this file belongs to decksaga/silentfail. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/decksaga/silentfail/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/decksaga/silentfail

Made for: Claude Code.

Wrote 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.

agentmods badge for silentfail CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/decksaga/silentfail/claude-md/github.svg)](https://agentmods.dev/instructions/decksaga/silentfail/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/decksaga/silentfail/claude-md"><img src="https://agentmods.dev/badge/instructions/decksaga/silentfail/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for silentfail CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/decksaga/silentfail/claude-md"><img src="https://agentmods.dev/badge/instructions/decksaga/silentfail/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 456 This file is loaded in full into every session.
When invoked 456 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00456 $0.00456
Opus 5.5 $0.00182 $0.00182
Sonnet 5.5 $0.00091 $0.00091
Haiku 4.5 $0.00046 $0.00046

Measured 2mo ago against content hash 82329a6e0d39, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

silentfail CLAUDE.md 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 2mo 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.

CLAUDE.md · 40 lines

What it actually says

SilentFail

Diagnostic tool for MCP servers. Discovers, tests, audits tokens, and scans for security issues across all major MCP clients.

Commands

  • Build: npm run build
  • CLI: node dist/index.js or silentfail (if linked via npm link)
  • Flags: --test (test each tool), --dashboard (web UI), --json (machine output), --help

Stack

TypeScript, Node.js 18+, ES modules, @modelcontextprotocol/sdk (client + server), zod/v4

Modes

  1. MCP Server (src/server.ts) — Claude Desktop calls scan_mcp_servers / open_silentfail_dashboard
  2. CLI (src/index.ts) — Terminal diagnostic with --test, --dashboard, --json

Key files

  • src/server.ts — MCP server (two tools exposed to Claude). Uses lazy imports to avoid SDK client/server conflict.
  • src/index.ts — CLI entry point
  • src/scanner.ts — Connects to servers, lists tools, tests them. Self-excludes silentfail to avoid recursion.
  • src/security.ts — Pattern-based scanner (50+ regex: injection, exfil, dangerous cmds, env vars, encoded payloads)
  • src/discovery.ts — Finds configs across Claude Desktop, Code, Cursor, VS Code, Windsurf, project-level
  • src/dashboard.ts — Web dashboard served on localhost with i18n (EN/ES)
  • src/types.ts — All TypeScript interfaces

Important

  • Server mode uses zod/v4 (NOT zod v3) — v3 silently fails to register tools
  • Lazy dynamic imports in server.ts prevent MCP Client/Server SDK conflicts
  • process.stdout.write is suppressed during scan in server mode to avoid corrupting JSON-RPC
  • Self-exclusion: scanner skips servers named "silentfail" or with args containing "silentfail/dist/server"

Skills

  • scan — Run when user asks to scan/diagnose MCP servers
Changes

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.

  1. 2mo ago First seen · 40 lines · 456 tokens per session scan A 82329a6e0d39

Subscribe to this mod's changes

silentfail CLAUDE.md is an instructions file published in the GitHub repository decksaga/silentfail (1 stars, last pushed 5mo ago), licensed MIT. It adds 456 tokens to every session, about $0.0018 per session on Opus 5.5. 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.

Debuggingai-toolsclaudedevtoolsdiagnosticsmcpmodel-context-protocol
Related

silentfail CLAUDE.md compared with instructions from other repositories

silentfail CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
silentfail CLAUDE.mddecksaga/silentfailInstructions file15mo agoMITA456Claude Code
vibetags com-example-service-TransactionalPaymentService.instructions.mdPIsberg/vibetagsInstructions file25yesterdayMITA104GitHub Copilot
vibetags com-example-gmm-platform-FeatureGate.mdPIsberg/vibetagsInstructions file25yesterdayMITA72Kiro
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode