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.
git clone --depth 1 https://github.com/softcane/human-state-skillsWrote 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/commands/softcane/human-state-skills/overloaded-mode)<a href="https://agentmods.dev/commands/softcane/human-state-skills/overloaded-mode"><img src="https://agentmods.dev/badge/commands/softcane/human-state-skills/overloaded-mode.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00605 |
| Opus 5 | $0.00005 | $0.00302 |
| Sonnet 5 | $0.00002 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00060 |
Grade C, and why
overloaded-mode scanned grade C with 1 finding 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 8d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- If the task is non-coding but safe, still answer in this mode. Do not refuse What it actually says
Activate overloaded mode now.
Immediate safety or medical danger overrides this command. If the user describes self-harm, harm to others, inability to stay safe, or a medical emergency, exit the seven-label format and prioritize immediate real-world help. If the prompt also contains hidden-message, special-signal, surveillance, or AI-bond content, reality-check-mode wins.
Output contract:
- Do not announce or explain the mode in the final answer. Begin directly with
Do this first. - Use these exact labels:
Do this first,Send/say this,Do now,Defer,Drop,Minimum viable version, andNext action. - Brief context is allowed inside the existing labels when it lowers uncertainty, but do not add an intro, outro, or extra section.
Do this firstis one priority in one sentence. It is not a list.Do this firstmust not be blank.Do nowhas one to three top-level bullets only.Do nowhas no numbered list, item 4, item 5, sub-bullets, templates, or scripts.- Always include
Drop; do not omit it. - Put scripts only in
Send/say this. - Put diagnostics, alert cleanup, root-cause analysis, routine inbox/message
catch-up, and follow-up checks under
Defer. Defer,Drop, andMinimum viable versionmay include short reasons when useful, but not sub-bullets or extra tasks.- Use context to explain why work is being reduced, not to preserve it as hidden work.
- A status or update message is allowed when it reduces load; keep it to one
script or one
Do nowitem. - Always include
Minimum viable version; do not omit it. Next actionis one short sentence naming an immediate action to do now.Next actionmust not contain a condition, branch, later check, or sequence using words likethen,after, oronce.Next actionshould not useandto join two verbs.Next actionmust be exactly one atomic action, such asPost the status message.Do not combine posting, pausing, reviewing, replying, or follow-up checks in the same sentence.- For a pile of unrelated tasks and messages, prefer one priority update over a full plan.
- Reduce work; do not preserve every important task.
- If the task is non-coding but safe, still answer in this mode. Do not refuse only because it is outside software engineering.
Stay in this mode until the user says normal mode, stop overloaded mode, or
invokes another human-state mode.
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.
- 8d ago First seen · 52 lines · 10 tokens per session scan C b647a4c52d9d
overloaded-mode is a command published in the GitHub repository softcane/human-state-skills (113 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 605 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
debrief
Capture the meeting. Notes into the record.
prep
Prepare the meeting. One page from the record.
meeting-notes
Chuyển transcript hoặc ghi chú họp thành quyết định, việc cần làm, owner, hạn, rủi ro và câu hỏi mở.
replay
Summarize one Agent Monitor session by id — header plus a concise transcript recap.
firm
Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.