This repository (Asymmetric-al/core)
These repo-owned sections sit above the official OpenSpec skill. Reconcile this
overlay after upstream refreshes before running bun run skills:sync.
Use the locally pinned CLI only: bun run openspec -- <command>. Do not invoke
@latest. Core does not use Stores. Pass an explicit change ID before any
mutating OpenSpec operation. Follow AGENTS.md and docs/ai/rules/openspec.md.
Do not bypass TDD, exact base-maia, data-access boundaries, security, or
repository checks. Do not archive unmerged or incomplete work. Do not run
openspec update against the live customized repository. Do not treat product
runtime Eve as a coding agent.
Allowed-tools metadata includes Bash(bun:*) so the local wrapper can run.
Triggers
- The matching OpenSpec workflow is requested: Explore, Propose, Update, Apply,
Verify, Sync, or Archive.
- Numbered commands
/1-start-project through /4-close-project wrap these
workflows.
Workflow
- Read
openspec/config.yaml, openspec/project.md, and the relevant specs
or active change.
- Invoke
bun run openspec -- with the explicit change ID for mutating work.
- Keep Core TDD, UI, data-boundary, and Guardian rules in force.
- Leave the change active until implementation has merged.
Checklist
Implement tasks from an OpenSpec change.
Project check: Before writing, run bun run openspec -- list --json and confirm the root is the Core checkout containing its local openspec/ tree. A missing root, Store declaration, or external root is a configuration error: stop before writing and report it. Do not initialize a root or select an external Store.
Input: Optionally specify a change name (e.g., /openspec-apply-change add-auth). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.
Steps
Select the change
If a name is provided, use it. Otherwise:
- Infer from conversation context if the user mentioned a change
- Auto-select if only one active change exists
- If ambiguous, run
openspec list --json to get available changes and ask the user to select one
Always announce: "Using change: " and how to override (e.g., /openspec-apply-change <other>).
Check status to understand the schema
openspec status --change "<name>" --json
Parse the JSON to understand:
schemaName: The workflow being used (e.g., "spec-driven")
planningHome, changeRoot, and actionContext: planning scope and edit constraints
- Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)
Get apply instructions
openspec instructions apply --change "<name>" --json
This returns:
contextFiles: artifact ID -> array of concrete file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)
- Progress (total, complete, remaining)
- Task list with status, source path, and source line
- Dynamic instruction based on current state
- Optional
context: current required project instruction input from the selected root
- Optional
operationGuidance: current advisory guidance for apply
missingArtifacts (when present): required artifact ids with no output
Handle states:
- If
state: "blocked": show the message and pause implementation.
- If
missingArtifacts is non-empty: verify whether /openspec-continue-change is installed before suggesting it. Core does not install it; if unavailable, use bun run openspec -- status --change "<name>" --json to identify the next artifact and bun run openspec -- instructions "<artifact-id>" --change "<name>" --json for its template and instructions. Creating the missing artifact is a separate authorized step; keep implementation paused.
- Otherwise, follow the CLI instruction to create or repair the schema-configured tracking file from existing planning artifacts. Do not assume another artifact is ready or start implementation while blocked.
- If
state: "all_done": report that all tracked tasks are complete and suggest review or verification as appropriate before archiving
- Otherwise: proceed to implementation
Treat context as a required prompt-level input. Read and consider it, and
apply relevant project facts, conventions, and constraints while implementing.
Treat operationGuidance as optional additive advice. Read and consider every
entry, and follow entries that are applicable and compatible with the built-in
workflow.
Keep both fields separate from CLI-returned state, missing artifacts, tasks,
progress, contextFiles, and the built-in instruction. They are not
evidence of task completion, do not replace the built-in instruction, and do
not permit bypassing a blocked state. If context conflicts with the built-in
instruction, an explicit user choice, or a CLI-controlled value, report the
conflict and preserve the controlling value. If guidance is inapplicable or
conflicts with those controlling inputs, do not follow it and explain why.
These are prompt-level behavior contracts, not enforceable checks.
Read context files
Read every file path listed under contextFiles from the apply instructions output.
The files depend on the schema being used:
- spec-driven: proposal, specs, design, tasks
- Other schemas: follow the contextFiles from CLI output
Do not copy context or operationGuidance verbatim into implementation
files or planning artifacts unless the user separately asks for that content.
Show current progress
Display:
- Schema being used
- Progress: "N/M tasks complete"
- Remaining tasks overview
- Dynamic instruction from CLI
Implement tasks (loop until done or blocked)
For each pending task:
- Show which task is being worked on
- Make the code changes required
- Keep changes minimal and focused
- Before editing, confirm the checkbox at the returned
sourcePath and line still matches the task description; if it does not, rerun the apply instructions and use the refreshed location
- Mark the task complete at its returned
sourcePath and line: - [ ] → - [x]
- Rerun the apply instructions and confirm that task is now done and progress changed
- Continue to next task
Pause if:
- Task is unclear → ask for clarification
- Implementation reveals a design issue → suggest updating artifacts
- A task needs work beyond what the spec and tasks describe, or you are tempted to drop, narrow, defer, or accept exceptions to specified behavior to make it fit → surface the added scope and ask; do not absorb it silently
- Error or blocker encountered → report and wait for guidance
- User interrupts
On completion or pause, show status
Display:
- Tasks completed this session
- Overall progress: "N/M tasks complete"
- If all done: report that tracked tasks are complete and suggest review or verification as appropriate before archiving
- If paused: explain why and wait for guidance
Output During Implementation
## Implementing: <change-name> (schema: <schema-name>)
Working on task 3/7: <task description>
[...implementation happening...]
✓ Task complete
Working on task 4/7: <task description>
[...implementation happening...]
✓ Task complete
Output On Completion
## Implementation Complete
**Change:** <change-name>
**Schema:** <schema-name>
**Progress:** 7/7 tasks complete ✓
### Completed This Session
- [x] Task 1
- [x] Task 2
...
All tracked tasks are complete. Review or verify the change as appropriate
before archiving. You can archive this change with `/openspec-archive-change`.
Output On Pause (Issue Encountered)
## Implementation Paused
**Change:** <change-name>
**Schema:** <schema-name>
**Progress:** 4/7 tasks complete
### Issue Encountered
<description of the issue>
**Options:**
1. <option 1>
2. <option 2>
3. Other approach
What would you like to do?
Guardrails
- Keep going through tasks until done or blocked
- Always read context files before starting (from the apply instructions output)
- If task is ambiguous, pause and ask before implementing
- If implementation reveals issues, pause and suggest artifact updates
- Keep code changes minimal and scoped to each task
- Update task checkbox immediately after completing each task
- Pause on errors, blockers, or unclear requirements - don't guess
- When a task needs work beyond what the spec describes, surface the added scope and pause - never silently narrow, defer, or simplify away specified behavior
- Only mark a task
- [x] when its specified behavior is fully implemented, not when it is partially done or deferred
- Use contextFiles from CLI output, don't assume specific file names
- Use each task's sourcePath and line to update its exact checkbox
- Do not use context or operation guidance as proof that a task is complete
- Apply relevant project context; report conflicts with controlling workflow inputs
- Consider every guidance entry; explain any inapplicable or conflicting advice
- Do not copy runtime context or operation guidance into implementation files or planning artifacts
- Preserve CLI-controlled blocked/ready/all-done behavior and completion criteria
Fluid Workflow Integration
This skill supports the "actions on a change" model:
- Can be invoked anytime: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
- Allows artifact updates: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly
1---2name: openspec-apply-change3description: Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks. Also use when the user says "openspec apply", "opsx apply", or "openspec implement".4allowed-tools: Bash(openspec:*), Bash(bun:*)5license: MIT6compatibility: Requires openspec CLI.7metadata:8 source: https://skillmd.com/skills/asymmetric-al/openspec-apply-change9 author: openspec10 version: "1.0"11---1213<!-- CORE-OVERLAY-START -->1415## This repository (Asymmetric-al/core)1617These repo-owned sections sit above the official OpenSpec skill. Reconcile this18overlay after upstream refreshes before running `bun run skills:sync`.1920Use the locally pinned CLI only: `bun run openspec -- <command>`. Do not invoke21`@latest`. Core does not use Stores. Pass an explicit change ID before any22mutating OpenSpec operation. Follow `AGENTS.md` and `docs/ai/rules/openspec.md`.23Do not bypass TDD, exact `base-maia`, data-access boundaries, security, or24repository checks. Do not archive unmerged or incomplete work. Do not run25`openspec update` against the live customized repository. Do not treat product26runtime Eve as a coding agent.2728Allowed-tools metadata includes `Bash(bun:*)` so the local wrapper can run.2930### Triggers3132- The matching OpenSpec workflow is requested: Explore, Propose, Update, Apply,33 Verify, Sync, or Archive.34- Numbered commands `/1-start-project` through `/4-close-project` wrap these35 workflows.3637### Workflow38391. Read `openspec/config.yaml`, `openspec/project.md`, and the relevant specs40 or active change.412. Invoke `bun run openspec --` with the explicit change ID for mutating work.423. Keep Core TDD, UI, data-boundary, and Guardian rules in force.434. Leave the change active until implementation has merged.4445### Checklist4647- [ ] Local pinned CLI used via `bun run openspec --`48- [ ] Explicit change ID used for mutating operations49- [ ] Stores were not introduced50- [ ] Incomplete or unmerged work was not archived51- [ ] `openspec update` was not run against the live repo52- [ ] Product Eve was not treated as a coding agent5354<!-- CORE-OVERLAY-END -->5556Implement tasks from an OpenSpec change.5758**Project check:** Before writing, run `bun run openspec -- list --json` and confirm the root is the Core checkout containing its local `openspec/` tree. A missing root, Store declaration, or external root is a configuration error: stop before writing and report it. Do not initialize a root or select an external Store.5960**Input**: Optionally specify a change name (e.g., `/openspec-apply-change add-auth`). If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.6162**Steps**63641. **Select the change**6566 If a name is provided, use it. Otherwise:67 - Infer from conversation context if the user mentioned a change68 - Auto-select if only one active change exists69 - If ambiguous, run `openspec list --json` to get available changes and ask the user to select one7071 Always announce: "Using change: <name>" and how to override (e.g., `/openspec-apply-change <other>`).72732. **Check status to understand the schema**7475 ```bash76 openspec status --change "<name>" --json77 ```7879 Parse the JSON to understand:80 - `schemaName`: The workflow being used (e.g., "spec-driven")81 - `planningHome`, `changeRoot`, and `actionContext`: planning scope and edit constraints82 - Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)83843. **Get apply instructions**8586 ```bash87 openspec instructions apply --change "<name>" --json88 ```8990 This returns:91 - `contextFiles`: artifact ID -> array of concrete file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)92 - Progress (total, complete, remaining)93 - Task list with status, source path, and source line94 - Dynamic instruction based on current state95 - Optional `context`: current required project instruction input from the selected root96 - Optional `operationGuidance`: current advisory guidance for apply97 - `missingArtifacts` (when present): required artifact ids with no output9899 **Handle states:**100 - If `state: "blocked"`: show the message and pause implementation.101 - If `missingArtifacts` is non-empty: verify whether `/openspec-continue-change` is installed before suggesting it. Core does not install it; if unavailable, use `bun run openspec -- status --change "<name>" --json` to identify the next artifact and `bun run openspec -- instructions "<artifact-id>" --change "<name>" --json` for its template and instructions. Creating the missing artifact is a separate authorized step; keep implementation paused.102 - Otherwise, follow the CLI instruction to create or repair the schema-configured tracking file from existing planning artifacts. Do not assume another artifact is ready or start implementation while blocked.103 - If `state: "all_done"`: report that all tracked tasks are complete and suggest review or verification as appropriate before archiving104 - Otherwise: proceed to implementation105106 Treat `context` as a required prompt-level input. Read and consider it, and107 apply relevant project facts, conventions, and constraints while implementing.108 Treat `operationGuidance` as optional additive advice. Read and consider every109 entry, and follow entries that are applicable and compatible with the built-in110 workflow.111112 Keep both fields separate from CLI-returned state, missing artifacts, tasks,113 progress, `contextFiles`, and the built-in `instruction`. They are not114 evidence of task completion, do not replace the built-in instruction, and do115 not permit bypassing a blocked state. If context conflicts with the built-in116 instruction, an explicit user choice, or a CLI-controlled value, report the117 conflict and preserve the controlling value. If guidance is inapplicable or118 conflicts with those controlling inputs, do not follow it and explain why.119 These are prompt-level behavior contracts, not enforceable checks.1201214. **Read context files**122123 Read every file path listed under `contextFiles` from the apply instructions output.124 The files depend on the schema being used:125 - **spec-driven**: proposal, specs, design, tasks126 - Other schemas: follow the contextFiles from CLI output127128 Do not copy `context` or `operationGuidance` verbatim into implementation129 files or planning artifacts unless the user separately asks for that content.1301315. **Show current progress**132133 Display:134 - Schema being used135 - Progress: "N/M tasks complete"136 - Remaining tasks overview137 - Dynamic instruction from CLI1381396. **Implement tasks (loop until done or blocked)**140141 For each pending task:142 - Show which task is being worked on143 - Make the code changes required144 - Keep changes minimal and focused145 - Before editing, confirm the checkbox at the returned `sourcePath` and `line` still matches the task description; if it does not, rerun the apply instructions and use the refreshed location146 - Mark the task complete at its returned `sourcePath` and `line`: `- [ ]` → `- [x]`147 - Rerun the apply instructions and confirm that task is now done and progress changed148 - Continue to next task149150 **Pause if:**151 - Task is unclear → ask for clarification152 - Implementation reveals a design issue → suggest updating artifacts153 - A task needs work beyond what the spec and tasks describe, or you are tempted to drop, narrow, defer, or accept exceptions to specified behavior to make it fit → surface the added scope and ask; do not absorb it silently154 - Error or blocker encountered → report and wait for guidance155 - User interrupts1561577. **On completion or pause, show status**158159 Display:160 - Tasks completed this session161 - Overall progress: "N/M tasks complete"162 - If all done: report that tracked tasks are complete and suggest review or verification as appropriate before archiving163 - If paused: explain why and wait for guidance164165**Output During Implementation**166167```168## Implementing: <change-name> (schema: <schema-name>)169170Working on task 3/7: <task description>171[...implementation happening...]172✓ Task complete173174Working on task 4/7: <task description>175[...implementation happening...]176✓ Task complete177```178179**Output On Completion**180181```182## Implementation Complete183184**Change:** <change-name>185**Schema:** <schema-name>186**Progress:** 7/7 tasks complete ✓187188### Completed This Session189- [x] Task 1190- [x] Task 2191...192193All tracked tasks are complete. Review or verify the change as appropriate194before archiving. You can archive this change with `/openspec-archive-change`.195```196197**Output On Pause (Issue Encountered)**198199```200## Implementation Paused201202**Change:** <change-name>203**Schema:** <schema-name>204**Progress:** 4/7 tasks complete205206### Issue Encountered207<description of the issue>208209**Options:**2101. <option 1>2112. <option 2>2123. Other approach213214What would you like to do?215```216217**Guardrails**218219- Keep going through tasks until done or blocked220- Always read context files before starting (from the apply instructions output)221- If task is ambiguous, pause and ask before implementing222- If implementation reveals issues, pause and suggest artifact updates223- Keep code changes minimal and scoped to each task224- Update task checkbox immediately after completing each task225- Pause on errors, blockers, or unclear requirements - don't guess226- When a task needs work beyond what the spec describes, surface the added scope and pause - never silently narrow, defer, or simplify away specified behavior227- Only mark a task `- [x]` when its specified behavior is fully implemented, not when it is partially done or deferred228- Use contextFiles from CLI output, don't assume specific file names229- Use each task's sourcePath and line to update its exact checkbox230- Do not use context or operation guidance as proof that a task is complete231- Apply relevant project context; report conflicts with controlling workflow inputs232- Consider every guidance entry; explain any inapplicable or conflicting advice233- Do not copy runtime context or operation guidance into implementation files or planning artifacts234- Preserve CLI-controlled blocked/ready/all-done behavior and completion criteria235236**Fluid Workflow Integration**237238This skill supports the "actions on a change" model:239240- **Can be invoked anytime**: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions241- **Allows artifact updates**: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly