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 commands/megamen32/lasthumancommit/askhumangit clone --depth 1 https://github.com/megamen32/LastHumanCommitWhat 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 | $0.00000 | $0.00401 |
| Opus 5 | $0.00000 | $0.00200 |
| Sonnet 5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
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.
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_humanwith 2-3 concretechoices; wait only when the answer truly blocks, otherwise keep working; - notification:
send_messagewith 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.
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 First seen · 43 lines · 0 tokens per session scan A dac8498bf437
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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.