askhuman

A command for sending one important message to a person through Telegram, a messaging service, using an already connected notification service.

In plain words
What is it for?
Asking for a decision, reporting a blocker, sharing progress while someone is away, and announcing completion.
Why use it?
It keeps people informed about decisions, blockers, timing, or long-running task completion without sending routine updates.

Command

Install

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.

agentmods
npx agentmods add commands/megamen32/lasthumancommit/askhuman
Clone the repo
git clone --depth 1 https://github.com/megamen32/LastHumanCommit
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 401 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00401
Opus 5 $0.00000 $0.00200
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured yesterday against content hash dac8498bf437, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

askhuman 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.

plugins/ask-human/commands/askhuman.md · 43 lines

What it actually says

Deliver something genuinely important to the human: a needed decision, a hard blocker, a timing/status answer, or long-cycle completion. One compact message through the already-connected AskHuman/notify MCP (Telegram). No new infrastructure.

When

  • a business decision or choice only the human can make;
  • a hard blocker the human must hear about immediately;
  • a timing/status answer while the human is away from the terminal;
  • completion of a long cycle the human asked to be told about.

How

  • decision: ask_human with 2-3 concrete choices; wait only when the answer truly blocks, otherwise keep working;
  • notification: send_message with a short title and the fact (expect_reply=false).

Rules

  • one compact message per matter; no spam; do not duplicate into the session chat when the user is clearly present;
  • NEVER use AskHuman for routine confirmations of reversible work — the consequential-action boundary stays with the active harness;
  • secrets never travel through AskHuman — use /secret (AskSecret) instead;
  • if the MCP is not connected, say so and continue in-session.

Endpoint — bring your own

The command is endpoint-agnostic: any AskHuman-compatible MCP works. Yours is configured per harness, not by the marketplace:

export LHC_ASKHUMAN_MCP_URL="https://your-notify.example/mcp"   # or .env
python3 plugins/ask-human/scripts/setup_mcp.py --apply          # registers it in Codex

LHC_ASKSECRET_MCP_URL does the same for /secret (--name AskSecret). Optional ..._MCP_TOKEN becomes a Bearer header. The script is dry-run by default and keeps a backup on --apply; for other harnesses it prints the snippet to add manually.

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. yesterday First seen · 43 lines · 0 tokens per session scan A dac8498bf437

Subscribe to this mod's changes

askhuman is a command published in the GitHub repository megamen32/LastHumanCommit (2 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 401 tokens. 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.