Execute each SDLC skill in a subagent — Closes #161#164
Merged
conradbzura merged 1 commit intowool-labs:mainfrom Apr 6, 2026
Merged
Execute each SDLC skill in a subagent — Closes #161#164conradbzura merged 1 commit intowool-labs:mainfrom
conradbzura merged 1 commit intowool-labs:mainfrom
Conversation
Each SDLC pipeline skill now executes inside a dedicated subagent rather than inline in the parent conversation context. Dispatcher files in llms/dispatchers/ spawn a general-purpose subagent that reads the corresponding skill definition from llms/skills/ and executes its workflow, returning a structured summary to the parent. This keeps the parent context clean for multi-step pipeline sessions.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Introduce a dispatcher layer (
llms/dispatchers/claude/) that wraps each SDLC pipeline skill in a dedicated subagent. Symlinks in.claude/commands/now point to dispatchers instead of directly to skill definitions. Each dispatcher spawns a general-purpose subagent that reads and executes the corresponding skill fromllms/skills/, keeping the parent conversation context clean for multi-step pipeline sessions. Skill definitions remain LLM-agnostic — subagent dispatch is an orchestration concern scoped to the harness-specific dispatcher layer. Dispatchers are organized by harness (dispatchers/claude/), leaving room for other harness implementations.Closes #161
Proposed changes
Subagent dispatchers
Add 7 dispatcher files in
llms/dispatchers/claude/— one for each SDLC skill (issue, implement, test, commit, pr, review, audit). Each dispatcher preserves the same frontmatter as its skill definition (maintaining command registration and trigger behavior) and contains a body that instructs the parent to spawn a subagent with the skill definition and arguments. The subagent handles all work — repository operations, file reads, planning, code generation, user approvals — and returns a structured summary.Documentation
Update
llms/README.mdto document the newdispatchers/claude/directory in the layout tree, add a Dispatchers section explaining the pattern and harness-scoped organization, and update the registration mechanism section to reflect that symlinks now target dispatchers. Also add the previously missingreview.mdentry to the skills directory listing.