Borrowing it
Nothing to install: this file belongs to lroolle/ihme-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lroolle/ihme-cli/main/CLAUDE.mdgit clone --depth 1 https://github.com/lroolle/ihme-cliWrote 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/lroolle/ihme-cli/claude-md)<a href="https://agentmods.dev/instructions/lroolle/ihme-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/lroolle/ihme-cli/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.
<a href="https://agentmods.dev/instructions/lroolle/ihme-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/lroolle/ihme-cli/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02715 | $0.02715 |
| Opus 5.5 | $0.01086 | $0.01086 |
| Sonnet 5.5 | $0.00543 | $0.00543 |
| Haiku 4.5 | $0.00271 | $0.00271 |
Grade A, and why
ihme-cli 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 today.
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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ihme-cli
iCloud Hide My Email CLI. Go + Cobra.
Build
make # build
make check # vet + test + build
make cross # cross-compile all platforms
Architecture
cmd/
ihme/main.go Entry point (version from ldflags)
root/root.go Root command, subcommand registration
auth/ login (SRP + 2FA), status, logout
list/ List with --search/--active/--inactive/--tag/--sort
new/ Generate candidates, interactive pick, --address to reserve
view/ View single address by ref
edit/ Edit label/note/tags
copy/ Copy address to clipboard
memorycmd/ Inspect the agent memory graph (path, search, graph, card)
lifecycle/ deactivate, reactivate, delete (with --yes confirmation);
several refs (IDs/addresses, no labels): all
resolved first, one confirmation, the first
failure stops the batch (many.go)
export/ CSV/JSON export with filters
forward/ forward-to management
share/ share <ref> | list | revoke: per-address access keys
serve/ ihme serve: the read-only web inbox (IMAP, app password
from --account/IHME_IMAP_*/em's accounts.json)
api/
types.go HmeEmail, SessionData, SavedCookie, auth types
endpoints.go URL constants, header maps
client.go HTTP client, manual Cookie header (rclone pattern), mergeCookies
auth.go SRP auth: start -> federate -> init -> complete -> 2FA -> trust -> accountLogin
session.go Session persistence to ~/.config/ihme/session.json
hme.go HME CRUD: list, generate, reserve, update, deactivate, reactivate, delete
internal/
srp/ SRP-6a (NG_2048, SHA-256, NoUserNameInX)
securitykey/ FIDO2 assertion over USB HID (cgo-free) for
security-key 2FA; touch only, no PIN
cmdutil/ GetClient, OutputResult, ExactRefArg, RefOrPick,
RefsOrPick (one or more <ref>s) +
PickAddress (omitted <ref> at a TTY -> newest-first
picker; never prompts without a TTY or with --json)
shares/ shares.json: address -> SHA-256(key); Grant rotates,
Revoke removes; the server re-reads it per request
inbox/ ihme serve: IMAP source (exact To/Cc check before any
row or body is shown), MIME -> text, HTTP + embedded
templates; the privacy model is its package doc
app/ Application service: the six HME operations
shared by Cobra commands and agent tools
(both are adapters over it)
agent/ Embedded-agent adapter: BYOK config,
in-process tools, scoped-consent gate,
renderer (see `ihme new --agent`); also the
harness side (`--via`, via.go) and the MCP
server (mcpserve.go) for `ihme mcp`
acp/ Minimal Agent Client Protocol client (v1
subset, hand-rolled): ihme as the HARNESS
spawning claude-code/codex/opencode as the
model provider — see `ihme agent --via`
memory/ Agent memory: a Logseq-style markdown graph
(journals/, pages/, flashcards). Plain files,
no DB — see its package doc
pkg/
output/ Table, JSON, CSV, detail formatters
filter/ --active/--inactive/--tag/--search/--sort
tags/ Parse/serialize #tag convention
resolver/ Universal ref resolver (ID, email, label fuzzy)
agentkit/ Embeddable agent kernel (stdlib-only, never
imports ihme packages — see its README)
skill/
SKILL.md Operational procedure shared by external
agents (shell) and the embedded agent
(go:embed, invoked as a task turn)
examples/
toyagent/ Minimal agentkit consumer (live smoke)
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.
- today Changed · +14 lines · +220 tokens per session 4c1cb4c5dd0f
- 22d ago Changed · +14 lines · +229 tokens per session 3acfdfa872b6
- 2mo ago First seen · 198 lines · 2,266 tokens per session scan A b409c8cffd2a
ihme-cli CLAUDE.md is an instructions file published in the GitHub repository lroolle/ihme-cli (3 stars, last pushed today), licensed MIT. It adds 2,715 tokens to every session, about $0.0109 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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.