Add or change behavior with design and end-to-end verification.
Pro scans all 2 files and shows the line behind each finding
Scanned 10/6/2026
npx -y skills add williamwue/oh-my-stack --skill feature --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Feature?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/williamwue-feature-oh-my-stack)More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.
---
name: feature
description: "Add or change behavior with design and end-to-end verification."
---
# Feature
## Codex delegation binding
For every delegated worker in this workflow, derive the exact `model`,
`reasoning_effort`, and complete role-plus-task `message` with
`../../scripts/codex-delegation.mjs prepare` relative to this Skill. It resolves
the nearest project manifest first, then the user manifest. Supply the named
route/panel entry where configured; otherwise supply the canonical role
and the observed parent model and effort. Pass
the returned `task_name`, `fork_turns=none`, model, effort, and message
explicitly to the spawn call. Do not use a generated custom-role name as a selector or
claim its TOML was activated. After the worker finishes, run the helper's
`verify` mode on the persisted parent and child records when available; it
checks the spawn metadata, parent link, and child `turn_context`.
The persisted spawn message may be encrypted; disclose when its exact
role/task text cannot be audited. If records are unavailable, state that
runtime model resolution is unverified.
For this workflow's implementers use `code.feature-refactoring`.
## Child session handoff
Read [the handoff contract](../poteto-mode/references/subagent-handoff.md).
New tasks, repair rounds, retries, and queue items use fresh child sessions
with the original brief, every later directive, prior findings and responses,
and unresolved objections. Reuse only for required costly live state, and
only when the host allows it. Stop and fence active writers before replacement.
A host-owned orchestrator's model catalog, workspace binding, child tools,
and review-round rules take precedence over the native binding above.
Keep its task handles and attribution receipts. Do not use a backing child
conversation as a new delegated review, or claim native-record verification
for a host-owned child. Report attribution evidence gaps explicitly.
The root owns design, integration, and proof.
1. Inspect the affected subsystem with the `how` workflow. Name the user-visible
behavior, current boundary, and the data shape that should organize the new
behavior.
2. Compare multiple designs only when the choice is consequential. Use a
`prototype` for an empirical fork and `interrogate` for a contested design.
Otherwise record why the direct design is sufficient.
3. Write a throughput checkpoint covering blocking gates, independent work,
shared mutable state, and the smallest safe decomposition. Use one writer
when ownership overlaps.
4. Establish failing or absent behavior with a test or executable reproduction
before implementation when practical.
5. Assign one bounded writer or implement at the root. A delegated writer gets
exact paths, the named data shape, constraints, and success commands. Use an
isolated workspace when available. Use the configured `code.feature-refactoring` route
when active; otherwise inherit the runtime model. If isolation is missing,
serialize writes and disclose it.
6. The root inspects the actual diff, rejects unrelated changes, and runs the
stated checks on the matching surface. Do not accept a child summary as
verification.
7. Keep commits small and independently verifiable. Do not publish or open a
pull request unless the user explicitly requested that external action.
Return what changed for the user, the chosen structure and tradeoffs, the
throughput checkpoint, exact verification commands and outcomes, evidence
limitations, and any open product decision.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!