fix: stop generate-rules-recon subagent from recursively spawning itself#79
Merged
Merged
Conversation
…itself The recon agent inherited every tool by default, including Agent and Skill. Its description closely mirrors the parent generate-rules skill's description, so mid-recon it would sometimes match its own task back to that skill and invoke it, which re-invokes the recon agent, recursing multiple levels deep before any real work happened. disallowedTools: Agent, Skill removes both from the recon agent's tool pool so it can no longer spawn subagents or invoke skills at all. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
|
Contributor
There was a problem hiding this comment.
Pull request overview
Prevents the generate-rules-recon worker agent from recursively re-invoking itself by restricting its tool surface, so recon remains read-only and reports findings back to the orchestrating generate-rules skill.
Changes:
- Add a
disallowedToolsrestriction to thegenerate-rules-reconagent to blockAgentandSkilltool usage.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
generate-rules-reconagent had notools/disallowedToolsrestriction, so it inherited every tool, includingAgentandSkill.generate-rulesskill's own description. Mid-recon, the subagent would sometimes match its own task back to that skill and invoke it via theSkilltool, which re-invokesgenerate-rules-reconvia theAgenttool — recursing multiple levels deep before doing any real recon work.Fix
Add
disallowedTools: Agent, Skilltoagents/generate-rules-recon.md, so the recon agent can no longer spawn subagents or invoke skills at all — it only does read-only reconnaissance and reports candidate rules back to the orchestrating skill.Test plan
/generate-rules(or/dolphin:generate-rules) against this repo and confirm the recon step completes without spawning nested recon agents.