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/adithyan-ak/agentmask/claude-mdgit clone --depth 1 https://github.com/adithyan-ak/agentmaskWrote 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/adithyan-ak/agentmask/claude-md)<a href="https://agentmods.dev/instructions/adithyan-ak/agentmask/claude-md"><img src="https://agentmods.dev/badge/instructions/adithyan-ak/agentmask/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 | $0.02326 | $0.02326 |
| Opus 5 | $0.01163 | $0.01163 |
| Sonnet 5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
agentmask 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 5d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentmask — Contributor Context
What This Is
agentmask is an open-source secrets firewall for AI coding agents. It prevents Claude Code, Cursor, and other AI assistants from reading, leaking, or committing secrets like API keys, tokens, passwords, and connection strings.
agentmask's value is the IDE integration layer — hooks, blocklist, MCP server, behavioral rules. Currently supports Claude Code and Cursor with auto-detection. Primary detection is delegated to gitleaks (150+ battle-tested rules). An agentmask scanner (src/scanner/tier2.ts) runs as a second pass to catch patterns gitleaks's generic-api-key rule deliberately excludes: password/passwd/pwd field assignments, connection strings with embedded credentials, and provider prefixes without dedicated gitleaks rules (whsec_, GOCSPX-).
Architecture
agentmask = IDE integration layer (Claude Code + Cursor)
├── Scanner backend: gitleaks (150+ rules, auto-downloaded if not installed)
├── agentmask scanner: complementary TS regex pass (password fields, conn strings, whsec_, GOCSPX-)
├── Blocklist manager (.agentmask/blocklist.json, shared between IDEs)
├── IDE adapters (src/ide/targets.ts — hook format, rules format, config paths per IDE)
├── Hooks (pre-read, pre-write, pre-bash, post-scan) with --format adapter
├── MCP server (safe_read, env_names, scan_file, scan_staged)
└── Behavioral rules (per-IDE: .claude/rules/*.md, .cursor/rules/*.mdc)
Three Reinforcing Layers
Layer 1: BLOCK (PreToolUse hooks)
→ Pre-read: static path patterns + dynamic blocklist lookup (no subprocess, <5ms)
→ Pre-write: gitleaks + agentmask scan on content via temp file (~200ms)
→ Pre-bash: pattern match on commands + gitleaks scan on staged files for git commit
→ Post-scan: gitleaks + agentmask scan on tool output, warns + auto-adds to blocklist
Layer 2: REDIRECT (MCP server)
→ safe_read: reads file, uses merged gitleaks + agentmask findings to redact secrets
→ env_names: lists .env variable names without values
→ scan_file / scan_staged: explicit scans (scan_file also runs agentmask scanner)
Layer 3: INSTRUCT (.claude/rules/agentmask.md)
→ Behavioral rules telling the agent to prefer safe_read
→ Installed automatically by `agentmask init`
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.
- 5d ago First seen · 185 lines · 2,326 tokens per session scan A 336b257162b8
agentmask CLAUDE.md is an instructions file published in the GitHub repository adithyan-ak/agentmask (12 stars, last pushed 5mo ago), licensed MIT. It adds 2,326 tokens to every session, about $0.0116 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.