Official recipe · Coding tasks
Translate agent configuration into checked target-platform files
Source-backed example. Practical decision guidance is proposed and untested; this is not a full implementation guide.
The problem
Moving agent configuration between platforms risks silently losing meanings that do not translate directly.
Agent job
Inspect the selected configuration, preview target files, repair incompatibilities and validate the translation.
Expected output
Target-platform configuration and a report of unresolved differences.
Where this framing comes from
- Core problem: Editorial purpose framing
- Agent job: Editorial purpose framing
- Expected output: Editorial purpose framing
- Relevant job roles: Editorial purpose framing
- Benefit type: Editorial purpose framing
Editorial framing and outcome limits
Describes the task’s purpose and intended output; measured benefit, safe unsupervised operation and successful delivery are not established by this framing.
Editorial synthesis based on the linked source. This framing does not add evidence of successful delivery or results.
Case-specific decision guidance · untested
Case-specific decision guidance and first checks are original proposals. The linked source supports the attributed task; this added guidance has not been executed.
Read the attributed source evidence and original caveats below ↓
Why use this
A developer moving agent configuration between platforms may discover that instructions, hooks and tool settings do not have exact equivalents. A generated target file can look syntactically plausible while changing behavior or accidentally including credentials.
This job could prepare a translation preview and semantic-difference report before any target files are changed. Keeping the source untouched and unsupported features explicit helps the owner evaluate migration scope rather than assume a mechanical conversion preserves everything.
Why an agent / simpler alternative
- Useful judgment
Map configuration intent, identify unsupported behavior and distinguish syntax repair from semantic equivalence.
- Simpler alternative
Rewrite a small configuration manually when few features need translation.
- Unsuitable when
The migration would copy secrets, overwrite unrelated files or treat source recipe permissions as authorization.
Proposed inputs
- Name
Selected configuration manifest
- Owner
Authorized owner
- Minimum scope
Only approved source files and feature descriptions
- Quality check
Exclude secrets and unrelated repositories
- Name
Target brief
- Owner
Owner
- Minimum scope
Selected destination, allowed generated artifacts and preservation rules
- Quality check
Confirm replacement versus preview scope
Access and setup — proposed or unknown
- Proposed minimum
Use fictional configuration entries and a proposed target manifest; no real config inspection, migration scripts or file replacement.
- Compatibility unknowns
Current platform semantics, migration-tool versions, validation support and runtime compatibility are unknown.
- External actions requiring approval
Reading private configuration, creating/replacing/deleting target files and changing persistent access requires explicit authorization.
Expected deliverable and review checks
- Proposed artifact
Migration-plan candidate with source-to-target mapping, unsupported features, proposed validation and protected-file boundaries.
- Critical checks
Preserve source files; exclude secrets; separate generated from unrelated artifacts; report semantic gaps even if syntax appears valid.
- Missing output evidence
This overlay adds no new output inspection, execution or validation; consult the referenced canonical source outcome limits.
Failure signals and proposed responses
- Signal
A source hook has no equivalent trigger
- Why it matters
The migrated behavior may run at the wrong time
- Proposed response
Mark it unsupported and request an explicit redesign choice.
- Signal
Cleanup targets include a hand-edited file
- Why it matters
Replacement can destroy intentional work
- Proposed response
Require file-level review and preserve the original.
Effort and cost — unknown
- Setup work
Define selected files and target ownership.
- Ongoing review
Owner reviews semantic differences and later authorized validation evidence.
- Unknowns
Feature equivalence, validation coverage, migration effort and tool costs are unknown.
First check — proposed, unexecuted
- Status
proposed_unexecuted
- Synthetic fixture
Invent a command, unsupported hook and secret-bearing setting plus a hand-edited target file; draft a migration preview only.
- Acceptance checks
Exclude the secret; flag semantic/overwrite risks; run no script or target validation.
- Stop conditions
Stop if file scope, replacement authority or behavior mapping is unclear.
Limits
A translation preview cannot establish target compatibility, semantic equivalence or safe persistent-access configuration.
Editorial candidate. This is source-backed reporting or a documented workflow. BotCurrent has not independently tested this task. A proposed Canadian adaptation is not evidence of a Canadian deployment or compliance certification.
Original source
https://github.com/openai/skills/blob/49f948faa9258a0c61caceaf225e179651397431/skills/.curated/migrate-to-codex/SKILL.md ↗Attributed to: OpenAI
Official recipe- Original action type
- coding_action
- What the source supports
- Inspect selected Claude Code instructions, commands, hooks, subagents and MCP settings; preview their translation into Codex artifacts; repair generated incompatibilities and rerun target validation; return a migration report with unresolved semantic differences.
- Source outcome limits
- This official recipe describes a procedure; it does not prove successful execution or independently reproduced results.
- Evidence attribution caveat
- This official recipe describes a procedure; it does not prove successful execution or independently reproduced results.
- Source approval description
- The recipe treats the user's selected target as permission to create, replace or delete generated Codex artifacts. It prohibits editing source Claude files, secrets, unrelated code or other repositories; replacement cleanup uses an explicit flag. These source instructions are not permission for this research.
- Named tools
- Codex; Python migrate-to-codex.py; scan, plan, doctor, dry-run and validate-target modes; AGENTS.md; .agents/skills; .codex configuration, hooks and agents
- Model or version
- Unknown
- Publication date
- Unknown
- Source last checked
- 2026-10-14
- Demonstrated in Canada
- Unknown
- Canadian availability
- Unknown
- Proposed Canadian adaptation
- Proposed: use an authorized Canadian team's configuration with secrets removed; confirm the target's data handling, tool access and bilingual team instructions before enabling migrated integrations.
- Recommended approval boundaries
- Approve the exact source/target paths and backup plan. Separately approve any deletion, credential handling, new persistent access, security-setting change or hook activation; do not inherit the source recipe's broad autonomy as authorization.