Route one OpenSpec change to the single-change archive workflow, or multiple changes to the bulk workflow. It requires specification deltas to be synced before archiving, validates before and after, and stops if syncing is blocked or validation fails.
Archive completed OpenSpec changes through the vendored archive workflows, delegating to the bundled $openspec-archive-change skill ($openspec-bulk-archive-change for two or more ids). Invoke via $oh-my-openspec:omos-archive.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Archive completed OpenSpec changes by delegating to the bundled vendored
archive skills — the Codex twin of OpenCode's archive command. Every
instruction line below is rendered from archiveInstruction in
core/prompts.ts, the same single source the OpenCode command prompts
with; the only transforms are the id-count branches pinned statically
and the skill names in the load lines rendered as $-mentions.
Arguments arrive as plain text in the user's message after the
$oh-my-openspec:omos-archive mention — there is no argument substitution. Split the
message on whitespace into change ids and follow the branch the id
count selects (the archiveSkillId mapping: zero or one id binds the
single-archive skill, two or more bind the bulk one):
$openspec-archive-change skill and follow it exactly.
No change ids given — list active changes, confirm with the user which to archive.$openspec-archive-change skill and follow it exactly.
Change: <change-id>$openspec-bulk-archive-change skill and follow it exactly.
Changes: <id-1>, <id-2>Follow each branch's steps in order:
Validate first with the openspec_validate tool; stop on INVALID unless the user explicitly overrides. Use the delegated archive skill for its other checks. These plugin-mandated steps override any conflicting upstream sync or archive choices: do not ask whether to sync, and stop before archiving if required sync is blocked. Sync the selected change's specification deltas into the main specs before archiving; do not ask whether to sync. When sync creates a new openspec/specs/<capability>/spec.md, give it a readable top-level title derived from the capability's purpose or meaning. Preserve existing authored titles and machine-named capability paths. If required specification sync is blocked, stop without archiving and report the blocker. After archiving, validate the resulting specifications. Repair issues that are safely fixable within OpenSpec artifacts, then validate again. If a post-archive issue requires code changes or cannot be safely repaired within OpenSpec artifacts, stop and report it without claiming validation passed.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan worthwhile local tasks by checking dependencies, effects, resources, and platform boundaries, then execute the exact approved plan. It can use safe parallel work or suitable Apple-silicon backends when the project exposes them.
Record deferred engineering decisions and temporary workarounds in a debt registry, with context such as effort, ongoing cost, affected area, and payoff trigger. Entries receive short labels so they can be reviewed or dropped later.
Generate or compare AI agent code for LangChain, EINO, AutoGen, AgentScope, and CrewAI using framework-specific templates, API mappings, conventions, and project structures. Reference files include verification dates to help identify potentially outdated guidance.
Investigate a reproducible bug, test failure, or unexpected page behavior, then make a narrowly scoped fix. The workflow calls for a regression test before changing code, verifies the fix, and reports remaining risks and evidence while avoiding unrelated refactoring or feature work.
Build an AI agent project through six collaborative stages, from requirements and architecture to tools, prompts, code generation, and verification. Start framework-independent, then generate a runnable project for frameworks such as LangChain, EINO, AutoGen, AgentScope, or CrewAI.
Audit a project or learning workflow for scope drift, conflicting plans, inconsistent names, and code quality concerns. The skill reads project files and code, then reports evidence, severity, and suggested next steps without changing files.