Add user-confirmation gate for MEMORY_INSTRUCTIONS in managed-memory skill - #261
Open
chvlsea wants to merge 1 commit into
Open
Add user-confirmation gate for MEMORY_INSTRUCTIONS in managed-memory skill#261chvlsea wants to merge 1 commit into
chvlsea wants to merge 1 commit into
Conversation
…skill Step 5 defined MEMORY_INSTRUCTIONS and jumped straight to Test, so agents running the skill routinely skipped surfacing the memory prompt to the user. Add an explicit confirmation step after the prompt, mirroring the Step 1 pattern that agents already honor: a bolded imperative, a mandated AskUserQuestion, and a gate that blocks the Test step until the user signs off. Synced to all five agent-* template copies. Co-authored-by: Isaac
jennsun
reviewed
Aug 20, 2026
| ``` | ||
|
|
||
| **Then confirm the instructions with the user before moving on — don't skip this.** Show them the full `MEMORY_INSTRUCTIONS` text you added and explain in a sentence or two what it controls: when the agent *recalls* memory (personalized questions) and what it *saves* (durable preferences, facts, and decisions — not passing chatter). **Ask with `AskUserQuestion`** whether to keep it as-is or change it — offer options like *"Looks good"*, *"Adjust when it saves/recalls"*, and *"I'll rewrite it"*. Apply whatever they ask for, matching the wording to the scope you chose in Step 1. **Don't proceed to Test until they've signed off.** | ||
|
|
Contributor
There was a problem hiding this comment.
If they pick either change option, can you continue in a normal chat message so it back and forth refines what the user wants?
nit but ...don't skip this. and Don't proceed to Test until they've signed off. say the same thing - keep the second one
jennsun
requested changes
Aug 20, 2026
jennsun
left a comment
jennsun
left a comment
Contributor
There was a problem hiding this comment.
can you confirm the workflow for updating instruction prompts is as intended after adding this skill? if you could include a recording/screenshots in PR description that would be great :)
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
2 participants
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.
What
Adds a step to the
managed-memoryskill (SKILL.md) requiring the agent to confirm theMEMORY_INSTRUCTIONStext with the user before proceeding to the Test phase.After adding
MEMORY_INSTRUCTIONS, the agent now:MEMORY_INSTRUCTIONStext it added.AskUserQuestionwhether to keep it as-is or change it (options like "Looks good", "Adjust when it saves/recalls", "I'll rewrite it").Why
Memory instructions materially shape agent behavior (what it stores and surfaces about the user). Giving the user an explicit review-and-confirm gate before finalizing avoids silently baking in defaults they didn't intend.
Scope
The change is applied to the canonical root skill and all five per-template copies (byte-identical, generated by
.scripts/sync-skills.py):.claude/skills/managed-memory/SKILL.md(root)agent-langgraph/,agent-langgraph-advanced/,agent-openai/,agent-openai-advanced/,agent-openai-agents-sdk/This pull request and its description were written by Isaac.