fix(skills): remove Agent Space references + sync WDS May improvements#34
Conversation
- Remove hardcoded Supabase URLs from start.md, wrap.md, handoff.md Handoffs now write to progress/[target_agent].md (file-based, no external dependency). Resumption via /[agent] progress/[agent].md. - Add src/data/wds-glossary.md — locked terminology for all agents - Add src/data/agent-contracts.md — domain boundaries, handoff rules, prerequisites, quality rules, out-of-scope per agent - Add src/data/shared-activation.md — common startup steps referenced by all agents instead of repeated inline - Fix src/tools/memory/SKILL.md: rename to wds-memory, remove WDS-E and external storage references Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
Warning Rate limit exceeded
You’ve run out of usage credits. Purchase more in the billing tab. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (7)
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
🤖 Augment PR SummarySummary: This PR removes Agent Space/Supabase dependencies from the WDS skills and aligns the workflow with a local, file-based session state and handoff mechanism. Changes:
Technical Notes: The wrap flow still updates 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
| ## Step: state | ||
|
|
||
| Check for session state via the memory tool. | ||
| Read `~/.claude/wds/src/tools/memory/SKILL.md` and follow the `load` operation for the current agent_id. |
There was a problem hiding this comment.
In src/data/shared-activation.md line 11, the docs hardcode an absolute ~/.claude/... path to the memory SKILL, which is likely to break on Windows or any install that places the module elsewhere. Can we confirm this path is guaranteed in all supported setups (including NPX/manual installs)?
Severity: medium
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
|
|
||
| **Step A — Save handoff via memory tool:** | ||
| Read `~/.claude/wds/src/tools/memory/SKILL.md` and follow the `save` operation: | ||
| - agent_id: [target_agent] |
There was a problem hiding this comment.
In src/skills/wrap.md line 161, the handoff save uses agent_id: [target_agent], which writes directly to progress/[target_agent].md and will overwrite any existing state file for that agent in the project. If concurrent/queued handoffs or an in-progress target-agent session are possible, this could cause state loss—worth confirming this overwrite behavior is intentional.
Severity: medium
Other Locations
src/skills/handoff.md:60
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
| - `progress/` should be in `.gitignore`. It is machine-local session context, not project content. | ||
| - Both save and load are synchronous file operations — no tokens, no async, no IDs. | ||
| - WDS-E replaces this file with `tools/memory/SKILL.md` that routes to Agent Space instead. The interface (save/load inputs and return values) is identical — only the storage destination changes. | ||
| - This is the canonical storage backend. State is local to the machine and project — not synced, not shared. |
There was a problem hiding this comment.
In src/tools/memory/SKILL.md line 51, the Notes describe state as machine-local and not shared, but earlier in the file it says the progress/ folder is “not per-machine.” This contradiction could confuse agents/users about whether session state should be expected to survive across machines.
Severity: low
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
| ``` | ||
| Post silently — do not wait for responses or report individual results. If Agent Space is unreachable, skip silently and continue. | ||
|
|
||
| **Step D — Confirm:** |
There was a problem hiding this comment.
In src/skills/wrap.md line 143, the subagent prompt jumps from “Step B” to “Step D” after the Agent Space section was removed. This can be confusing when following the instructions verbatim, especially since the prompt emphasizes exact execution.
Severity: low
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
1 participant
Summary
start.md,wrap.md, andhandoff.md— these should never have been in a public BMad module. Handoffs now write toprogress/[target_agent].md(file-based). Agent picks up via/[agent] progress/[agent].md.src/data/wds-glossary.md— locked terminology for all agents (phases, artifacts, model selection, patterns)src/data/agent-contracts.md— domain boundaries, prerequisites, handoff rules, out-of-scope per agentsrc/data/shared-activation.md— common startup steps (state, scan, select, brownfield-detect) referenced by all agentssrc/tools/memory/SKILL.md— rename towds-memory, remove WDS-E/external storage referencesTest plan
npx bmad-method install/wrap mimirwrites toprogress/mimir.md(no external call)/handoff freyawrites toprogress/freya.md/startreadsprogress/[agent].mdand shows resume prompt🤖 Generated with Claude Code