Skip to content

docs(agents): sync shared working rules from ai-rules - #3881

Merged
BigSimmo merged 1 commit into
mainfrom
rules/shared-rules-sync-20261101
Nov 1, 2026
Merged

BigSimmo merged 1 commit into
mainfrom
rules/shared-rules-sync-20261101

Conversation

@BigSimmo

@BigSimmo BigSimmo commented Nov 1, 2026 •

Copy link
Copy Markdown
Owner

Updates this repository's copies of Josh's shared working rules to the current reviewed public projection from BigSimmo/ai-rules (generated by repository_rule_targets.py, the same logic as sync.sh --repos).

Changed: only the managed shared-cloud-working-rules block in AGENTS.md and the shared prefix of docs/agents/shared-context-and-memory.md. Any project-owned addendum is preserved byte-for-byte; the generator refuses to overwrite unreviewed edits.

Main additions: authorized browser/device testing preference (Chrome, then Edge), reporting missing capability precisely, leaner process guidance, the parallel dev server memory check, and condensed memory-budget wording. No product, clinical or runtime behaviour changes.

Checks: generated from a clean worktree of origin/main. Local docs-link and inventory checks pass; the full docs-maintenance check could not run locally (a formatting dependency was missing in the temporary worktree; it fails identically without this change), so CI is the authority.

Note for local checkouts: the main checkout carries an older uncommitted copy of these two files from an earlier sync. Once this merges, those two local changes are superseded and can be discarded before pulling.


Summary by cubic

Syncs the managed shared working rules from BigSimmo/ai-rules into AGENTS.md and docs/agents/shared-context-and-memory.md. Only the managed shared blocks change; project-owned content is preserved byte-for-byte. This is documentation-only — no product, clinical, or runtime behavior changes.

Key changes

  • Authorized browser/device testing now prefers Chrome then Edge and requires reporting exact missing capability.
  • Spending approval moves from per-run gates to one bounded-task approval covering reasonable iterations and retries.
  • Adds the parallel dev-server memory check for multi-agent browser work and condenses the memory-budget wording.

Local checkouts may carry stale uncommitted copies of these two files from an earlier sync; discard them before pulling once this merges. The full docs-maintenance check could not run locally (missing formatting dependency; it fails identically without this change), so CI is authoritative.

Written for commit 7f9ab24. Summary will update on new commits.

View guided diff


Summary by Gitar

  • PR repair workflow:
    • Adds guidance for authorized PR repairs: inspect head, threads, checks and mergeability, then fix the first failing layer
    • Requires verifying the remote head and checks after an authorized push, without weakening checks to go green
  • Trusted approvals and skills:
    • Requires exact task approvals to pass through the host's trusted handoff, not agent summaries
    • Limits skill use to relevant references and avoids duplicate plans or approvals

This will update automatically on new commits.

Summary by CodeRabbit

  • Documentation
    • Updated guidance for browser and device verification, including resource considerations for running isolated browser sessions.
    • Clarified task approval and spending limits, including approval scope, estimated costs, and when additional approval is needed.
    • Revised guidance for delegation, task checkpoints, review and repair steps, access boundaries, and saving project information.

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Nov 1, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ✅ Completed 2026-11-01T11:13:52.981036Z 7f9ab24 PR opened
ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

@claude

claude Bot commented Nov 1, 2026 •

Copy link
Copy Markdown
Contributor

Claude encountered an error after 2s —— View job


I'll analyze this and get back to you.

@coderabbitai

coderabbitai Bot commented Nov 1, 2026 •

Copy link
Copy Markdown
Contributor

Review in Change Stack →

No actionable comments were generated in the recent review.

Recent review info
Run configuration
Commits

Reviewing files that changed from the base of the PR and between 488f7c3 and 7f9ab24.

Files selected for processing: 2
  • AGENTS.md
  • docs/agents/shared-context-and-memory.md

Included review availability: This review used your included allowance. 0 included reviews remain after this review. Your included PR review attempts over the past 7 days set your current allowance at 1 review per hour.

Walkthrough

Shared agent guidance now defines updated task authorization, browser verification, delegation, reporting, and memory-saving procedures. Spending guidance replaces per-run approval with bounded approval for named tasks or evaluation batches.

Changes: Agent workflow and spending rules

Layer / File(s) Summary
Task authorization and execution guidance
AGENTS.md, docs/agents/shared-context-and-memory.md
The guidance updates browser and device verification, task-local authorization, delegation, task records, and reporting. It also distinguishes project-memory saving requirements from otherwise authorized work.
Bounded billable-work approvals
AGENTS.md, docs/agents/shared-context-and-memory.md
Approval now covers a named task or evaluation batch with specified services, estimated cost, currency, and maximum spend. The guidance defines when approval must be renewed and requires tracking usage against the cap.

Estimated code review effort: 2 (Simple) | ~10 minutes

Change: Other

Possibly related PRs

  • BigSimmo/PsychSift#3845: Changes the same managed rule blocks and covers memory-save and spending approval rules.
  • BigSimmo/PsychSift#3781: Changes approval guidance for live database, worker, and OpenAI commands; this PR updates shared authorization guidance.
  • BigSimmo/PsychSift#3859: Defines approval requirements for retrieval evaluations; this PR updates the bounded approval policy for evaluation batches.

Suggested reviewers: claude

Merge Risk: Minimal · up to 7f9ab

The updated spending guidance remains authoritative. No actionable merge-blocking risk was established.

Pre-merge checks: Passed 5
Check name Status Explanation
Title check Passed The title clearly identifies a documentation sync of shared working rules from ai-rules. It is concise and specific to the main change.
Description check Passed The description clearly explains the scope, preserved content, main additions, verification status, and lack of product or clinical behavior changes. It does not use every template heading and does no…
Docstring Coverage Passed No eligible functions found in the changed files. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff with cyclomatic complexity of at least 2. Documentat…
Linked Issues check Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check Passed Check skipped because no linked issues were found for this pull request.
Full details: Description check

Explanation

The description clearly explains the scope, preserved content, main additions, verification status, and lack of product or clinical behavior changes. It does not use every template heading and does not explicitly state rollback or provider effects, but the missing details are non-critical for this documentation-only change.

Full details: Docstring Coverage

Explanation

No eligible functions found in the changed files. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff with cyclomatic complexity of at least 2. Documentation-only edits and deletions within surviving functions are included; unchanged diff context and fully deleted functions are excluded. Analyzed 0 functions across 0 files. (2 skipped: 2 unsupported.)

Finishing Touches
Generate unit tests (beta)
  • Commit to this branch
  • Create a new PR
  • Autofix · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

@gitar-bot

gitar-bot Bot commented Nov 1, 2026

Copy link
Copy Markdown
Contributor

Important

You are using the Gitar free plan. Upgrade to unlock code review, CI analysis, auto-apply, custom automations, and more.

Gitar

@supabase

supabase Bot commented Nov 1, 2026

Copy link
Copy Markdown

This pull request has been ignored for the connected project sjrfecxgysukkwxsowpy because there are no changes detected in supabase directory. You can change this behaviour in Project Integrations Settings ↗︎.


Preview Branches by Supabase.
Learn more about Supabase Branching ↗︎.

@BigSimmo
BigSimmo merged commit 08fbeda into main Nov 1, 2026
38 of 40 checks passed
@BigSimmo
BigSimmo deleted the rules/shared-rules-sync-20261101 branch November 1, 2026 12:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant