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 skills/heapy/kortex/message-claudenpx skills add Heapy/kortex --skill message-claudegit clone --depth 1 https://github.com/Heapy/kortexWhat 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 | $0.00123 | $0.00752 |
| Opus 5 | $0.00062 | $0.00376 |
| Sonnet 5 | $0.00025 | $0.00150 |
| Haiku 4.5 | $0.00012 | $0.00075 |
Grade A, and why
message-claude 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Message Claude
Find the exact Claude Code session and send it one plain-text message.
For the opposite direction, use Message Codex.
If ListAgents and SendMessage are available, use them. Do not use the raw inbox to bypass a
permission rule that denied either tool. The workflow below is for external callers such as a
standalone Codex session, Codex launched by Claude, a hook, or a script.
The bundled helper supports macOS, Linux, and WSL 2. Native Windows uses a named pipe and is not implemented here.
Send a message
Resolve scripts/message_claude.py from this skill's directory.
-
List the registered sessions:
python3 <skill-dir>/scripts/message_claude.py --list -
Select the target by its exact
name. If names repeat, narrow with--cwdor--pid. Never guess between multiple matches. -
Send a short message:
python3 <skill-dir>/scripts/message_claude.py \ --name the-session-name \ --message 'codex: the migration finished; tenant_id is the new column'Omit
--messageto read arbitrary or multiline text from stdin.
The helper uses --config-dir, then CLAUDE_CONFIG_DIR, then ~/.claude. Pass --config-dir
when Claude uses a custom directory that the caller did not inherit.
What the helper guarantees
- Reads
<config-dir>/sessions/*.jsonand refuses zero or multiple target matches. - Reads the target's
peerTokenwithout printing it. The key filename hashesmessagingSocketPathexactly as recorded; it does not resolve/tmpto/private/tmp. - JSON-encodes the complete auth and message payload before connecting, so quotes, newlines, and backslashes in the message remain valid.
- Reports a successful socket write, not guaranteed delivery. The receiving session may still
hold or refuse the message through
crossSessionInbound.
Failures
- No matching session: list again and check
name,cwd,pid, and--config-dir. - Connection failure: the registry entry may be stale; list again instead of retrying blindly.
- Permission error: the Codex sandbox may block that Unix socket. Report the socket path and ask for a grant scoped to its directory; do not bypass the sandbox.
- Missing
peerToken: stop and verify the config directory and target rather than sending an unauthenticated message.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 68 lines · 123 tokens per session scan A 244c544e79c7
message-claude is a skill published in the GitHub repository Heapy/kortex (6 stars, last pushed 4d ago), licensed Apache-2.0. It adds 123 tokens to every session and 752 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
mobile-experience-report
Use when the user says 'my site looks bad on mobile', 'check mobile layout', 'responsive audit', or 'site broken on phones'. Diagnoses breakpoint problems, text sizing, column stacking failures, hidden elements, and navigation menu behavior, device by device.
motherduck-design-dive
Design or redesign a MotherDuck Dive as a responsive, reusable analytics interface. Use when a Dive must be mobile-friendly from the start, support light and dark modes, reserve space for filters, use restrained Power BI-style information design, embed small charts inside metric components, or work across customers…
desktop-expert
Compose Multiplatform Desktop patterns for the desktopApp/ module. Use when working with (1) Desktop-only APIs (Window, WindowState, Tray, MenuBar, Dialog), (2) keyboard shortcuts and menu systems with OS-aware conventions (Cmd vs Ctrl, isMacOS branching), (3) desktop navigation (NavigationRail/sidebar vs Android…
gradle-expert
Build optimization, dependency resolution, and multi-module KMP troubleshooting for AmethystMultiplatform. Use when working with: (1) Gradle build files (build.gradle.kts, settings.gradle), (2) Version catalog (libs.versions.toml), (3) Build errors and dependency conflicts, (4) Module dependencies and source sets, (5)…
add-native
Public entry point for native device capabilities and native controls — camera, image picker, barcode/QR scanner, document picker, file picker, secure storage, file system, sharing, PDF generation/viewing, pen/signature capture, background GPS/geolocation tracking, or supported local file workflows — in a Power Apps…
amy-expert
Patterns for extending amy, the Amethyst CLI in cli/. Use when adding an amy command, touching files under cli/src/main/kotlin/…/cli/, wiring a new subcommand into Main.kt, writing an interop test script that drives Amy, or extracting logic out of amethyst/ into commons/ so a CLI command can call it. Enforces the…