Never Block on the Human
The human supervises asynchronously. Agents must stay unblocked. Make reasonable decisions, proceed, and let the human course-correct after the fact.
Why: Every permission pause stalls the pipeline and makes the human the bottleneck. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking.
Pattern:
- Proceed, then present. Do the work, show the result. Don't ask "should I do X?" Do X, explain why.
- Make the system self-healing. When you notice a problem, log it and fix it in the next round.
Boundaries:
- Irreversible actions (force-push, delete production data, send external messages) still require confirmation.
- Reversible actions (write code, edit notes, split tasks) should proceed without blocking.
- Product direction comes from the human. Execution should not block.
This repository (Asymmetric-al/core)
Vendored from p3-stack (MIT) at commit 09909eb. Provenance is in references/upstream.md. On conflict, the current user request, root AGENTS.md, the nearest nested AGENTS.md, and the matching docs/ai/rules/* rulebook win over this skill.
- Explicit invocation only: use it when the user invokes
/principle-never-block-on-the-human (Claude Code, Cursor, T3 Code) or $principle-never-block-on-the-human (Codex), or when an invoked p3-stack skill routes here. Do not route other work to it.
- Confirm before outward-facing or hard-to-reverse actions such as pushing, merging, deploying, deleting, or posting messages, unless the user authorized that action for this task.
- Core's approval boundaries define what counts as reversible here. Pushing, merging, posting messages, filing tickets, and deleting anything you did not create in this task still need the user's authorization.
Edit this canonical copy in docs/ai/skills/principle-never-block-on-the-human/, then run bun run skills:sync and bun run skills:verify.
1---2name: principle-never-block-on-the-human3description: "Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions."4disable-model-invocation: true5metadata:6 source: https://skillmd.com/skills/asymmetric-al/principle-never-block-on-the-human7---89# Never Block on the Human1011The human supervises asynchronously. Agents must stay unblocked. Make reasonable decisions, proceed, and let the human course-correct after the fact.1213**Why:** Every permission pause stalls the pipeline and makes the human the bottleneck. Since code changes are reversible and reviewable, a wrong decision usually costs less than blocking.1415**Pattern:**1617- **Proceed, then present.** Do the work, show the result. Don't ask "should I do X?" Do X, explain why.18- **Make the system self-healing.** When you notice a problem, log it and fix it in the next round.1920**Boundaries:**2122- **Irreversible actions** (force-push, delete production data, send external messages) still require confirmation.23- **Reversible actions** (write code, edit notes, split tasks) should proceed without blocking.24- **Product direction** comes from the human. _Execution_ should not block.2526<!-- CORE-OVERLAY-START -->2728## This repository (Asymmetric-al/core)2930Vendored from [p3-stack](https://github.com/uzairansaruzi/p3-stack) (MIT) at commit `09909eb`. Provenance is in `references/upstream.md`. On conflict, the current user request, root `AGENTS.md`, the nearest nested `AGENTS.md`, and the matching `docs/ai/rules/*` rulebook win over this skill.3132- Explicit invocation only: use it when the user invokes `/principle-never-block-on-the-human` (Claude Code, Cursor, T3 Code) or `$principle-never-block-on-the-human` (Codex), or when an invoked p3-stack skill routes here. Do not route other work to it.33- Confirm before outward-facing or hard-to-reverse actions such as pushing, merging, deploying, deleting, or posting messages, unless the user authorized that action for this task.34- Core's approval boundaries define what counts as reversible here. Pushing, merging, posting messages, filing tickets, and deleting anything you did not create in this task still need the user's authorization.3536Edit this canonical copy in `docs/ai/skills/principle-never-block-on-the-human/`, then run `bun run skills:sync` and `bun run skills:verify`.3738<!-- CORE-OVERLAY-END -->