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/secretgit 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 | $0.00344 |
| Opus 5 | $0.00000 | $0.00172 |
| Sonnet 5 | $0.00000 | $0.00069 |
| Haiku 4.5 | $0.00000 | $0.00034 |
Grade A, and why
secret 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
/secret — hand a secret to the agent from the phone
Usage: /secret NAME [target]
NAME— the environment variable name to set (for exampleAPI_KEY).target— optional destination file; default.envin the current project.
The whole operation is a few steps, produces no lectures, and never builds new secret infrastructure.
Flow
- If an AskSecret MCP is connected (tools like
ask_secret,get_secret,ask_secret_run), callask_secret(NAME). The user receives a phone prompt and pastes the secret there. When the secret is ready,get_secretreturns an opaque file/URL: pipe the file content straight into the target (appendNAME=<value>to.env, or export it for the process) in one command, without reading, printing, or echoing the value into chat or logs. - Otherwise, if AskHuman/notify (Telegram) is available, send one short
message asking the user to deliver
NAME(AskSecret link or direct paste), wait for the reply, and write it to the target the same way. - Otherwise ask in chat for the value, write it to the target immediately, and do not quote it back.
Rules
- Confirm completion only as
NAME set in <target>; never echo the value. - Later reads of the secret are a normal one-step env/
.envread. - Do not demand attestation, do not create handoff layers, and do not insert confirmation prompts for this routine operation.
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 · 31 lines · 0 tokens per session scan A e496eb75a7a2
secret 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 344 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.