dilim/skills
1
0
Fork 0
mirror of https://github.com/mattpocock/skills.git synced 2026-08-07 08:31:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: make subagent dispatch harness-neutral

Browse Source 
Three skills named Claude Code's `Agent` tool and its `general-purpose`
and `Explore` agent types directly. The repo installs across Claude Code,
Codex, and other Agent-Skills harnesses, none of which share that tool or
those type names, so the instruction was unfollowable outside Claude Code.

Each site now describes the shape of the dispatch — parallel subagents,
and what capability each one needs — and leaves the mechanism to the
harness.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Matt Pocock
2026-08-06 13:58:35 +01:00
parent 8b36d4fb26
commit 14bfbbd865
4 changed files with 10 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
.changeset/harness-neutral-subagent-language.md Normal file
View File

@@ -0,0 +1,7 @@
---
"mattpocock-skills": patch
---
Make the subagent-dispatch instructions harness-neutral.
`code-review`, `codebase-design`'s `DESIGN-IT-TWICE.md`, and `improve-codebase-architecture` named Claude Code's `Agent` tool and its `general-purpose` / `Explore` agent types directly. Codex and other Agent-Skills harnesses have no such tool or type, so the instruction was unfollowable there. Each now describes the *shape* of the dispatch — parallel subagents, and what capability each one needs — and leaves the mechanism to the harness.

2
skills/engineering/code-review/SKILL.md
View File

@@ -57,7 +57,7 @@ Each smell reads *what it is* → *how to fix*; match it against the diff:
### 4. Spawn both sub-agents in parallel
Send a single message with two `Agent` tool calls. Use the `general-purpose` subagent for both.
Dispatch both with your harness's subagent mechanism, in parallel — one message with two calls where the harness supports it. Pick its most general-purpose agent for both: each must read files and run `git`, so a search-only agent is too narrow.
**Standards sub-agent prompt** — include:

2
skills/engineering/codebase-design/DESIGN-IT-TWICE.md
View File

@@ -18,7 +18,7 @@ Show this to the user, then immediately proceed to Step 2. The user reads and th
### 2. Spawn sub-agents
Spawn 3+ sub-agents in parallel using the Agent tool. Each must produce a **radically different** interface for the deepened module.
Spawn 3+ sub-agents in parallel with your harness's subagent mechanism. Each must produce a **radically different** interface for the deepened module.
Prompt each sub-agent with a separate technical brief (file paths, coupling details, dependency category from [DEEPENING.md](DEEPENING.md), what sits behind the seam). The brief is independent of the user-facing problem-space explanation in Step 1. Give each agent a different design constraint:

2
skills/engineering/improve-codebase-architecture/SKILL.md
View File

@@ -24,7 +24,7 @@ This command is _informed_ by the project's domain model and built on a shared d
Read the project's domain glossary (`CONTEXT.md`) and any ADRs in the area you're touching first.
Then use the Agent tool with `subagent_type=Explore` to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
Then dispatch a subagent to walk the codebase — a read-only exploration agent if your harness has one. Don't follow rigid heuristics — explore organically and note where you experience friction:
- Where does understanding one concept require bouncing between many small modules?
- Where are modules **shallow** — interface nearly as complex as the implementation?