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/ashlrai/phantom-secrets/claude-mdgit clone --depth 1 https://github.com/ashlrai/phantom-secretsWrote 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/ashlrai/phantom-secrets/claude-md)<a href="https://agentmods.dev/instructions/ashlrai/phantom-secrets/claude-md"><img src="https://agentmods.dev/badge/instructions/ashlrai/phantom-secrets/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 | $0.01137 | $0.01137 |
| Opus 5 | $0.00568 | $0.00568 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
phantom-secrets 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phantom — Development Guide
Quick Reference
# Build
~/.cargo/bin/cargo build
# Test
~/.cargo/bin/cargo test
# Lint (must pass with zero warnings)
~/.cargo/bin/cargo clippy --all-targets -- -D warnings
# Format
~/.cargo/bin/cargo fmt --all
# Run CLI
~/.cargo/bin/cargo run -- <command>
Note: ~/.cargo/bin/ prefix is needed because cargo is not in PATH on this machine.
Architecture
Modular Rust workspace with a shipped secret-protection product and separate fail-closed governed-execution foundations:
- phantom-core — Config (.phantom.toml), .env parsing/rewriting, phantom token generation (256-bit CSPRNG,
phm_prefix), error types - phantom-vault —
VaultBackendtrait with OS keychain (macOS Keychain, Linux Secret Service, Windows Credential Manager) and encrypted file fallback. Argon2id parameters hardened to OWASP balanced (m=64 MiB, t=3, p=1) with legacy-default fallback for older vaults - phantom-proxy — HTTP reverse proxy on 127.0.0.1. It authenticates and matches exact routes, discards client control of the route auth header, injects only the route-owned vault value there, and forwards client bodies byte-for-byte under a hard size cap. Client headers/bodies never resolve
phm_tokens. Useshyperfor server andreqwestfor outbound HTTPS; response streaming/SSE is preserved through scrubbing. - phantom-cli —
clap-based CLI for init, proxy execution, diagnostics, sync, teams, audit, validation, provider design foundations, and trusted-terminal workspace setup. Live provider issuance/rotation is hard-denied before credential/network access in 0.7.5. Usephantom --helpas the canonical command inventory. Plaintext JSON export is disabled; reveal requires an attached terminal and exact typed confirmation. - phantom-mcp — MCP server for Claude Code, Cursor, Windsurf, Codex. Uses
rmcp1.3 SDK and stdio transport. Exposes core vault/diagnostic/cloud/team tools plus advanced audit, validation, rotation, expiry, leak-incident, and compliance workflows. The exact catalog is declared incrates/phantom-mcp/src/server.rs. - governed-execution foundations —
phantom-workspaceprovides the active value-blind Unix setup transaction.phantom-authority,phantom-locus-contract,phantom-broker,phantom-runtime,phantom-session, andphantom-evidenceremain fail closed for production execution.
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.
- yesterday Changed · +2 lines · -102 tokens per session 7db20c48f23f
- 5d ago First seen · 61 lines · 1,239 tokens per session scan A 5fb054ca29d0
phantom-secrets CLAUDE.md is an instructions file published in the GitHub repository ashlrai/phantom-secrets (16 stars, last pushed today), licensed MIT. It adds 1,137 tokens to every session, about $0.0057 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
node9-proxy CLAUDE.md
Claude Code instructions for node9-ai/node9-proxy, covering node9 proxy — claude code rules, pr checklist (required before every commit), test rules, code rules and architecture notes.
dsh-auto-review AGENTS.md
AGENTS.md instructions for PerryLink/dsh-auto-review, covering agents.md, layout, hard rules applied here, build and docs.
orloj AGENTS.md
AGENTS.md instructions for OrlojHQ/orloj, covering orloj agent instructions, must-follow sync rules and working style.
agent47 CLAUDE.md
Claude Code instructions for bmdhodl/agent47, covering claude.md, read first, repo boundary, claude repo contract and what claude should optimize for here.
nuclear-grade-context-engineering AGENTS.md
Instructions for FlyFission/nuclear-grade-context-engineering, covering agent guidance, default behavior, verification routing, authority boundaries and skill loading rule.
sysknife CLAUDE.md
Claude Code instructions for lacs-project/sysknife, covering sysknife operating notes, current focus — ubuntu; gui paused, pre-commit gate, repository workflow and worktree convention.