Conversation
Extracts common patterns from google-app-scripts, broodly, and TalkTerm into a shared AGENTS.md that individual repos can import. Covers TDD, pre-commit checks, CI gates, PR reviews, security, and agent guidance. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
📝 WalkthroughWalkthroughAdds Changes
Sequence Diagram(s)(omitted) Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes 🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Comment |
2 tasks
Contributor
There was a problem hiding this comment.
Pull request overview
Adds an organization-wide AGENTS.md intended to be imported by individual repositories, consolidating shared engineering and agent-operation standards across the petry-projects org.
Changes:
- Introduces org-level standards for TDD, pre-commit checks, CI quality gates, and PR review handling
- Adds security/secret-handling guidance and planning artifact conventions
- Documents agent-operation guidelines and reference links
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
This was referenced Mar 28, 2026
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@AGENTS.md`:
- Around line 56-60: The fenced code block containing the GraphQL example (the
line starting with "gh api graphql -f query='mutation { resolveReviewThread...")
violates markdownlint MD031; fix it by adding a blank line immediately before
the opening triple-backticks and a blank line immediately after the closing
triple-backticks so the GraphQL command block is separated from surrounding text
and the following sentence about retrieving thread IDs with a reviewThreads
query.
- Line 16: Update the policy sentence at Line 16 to distinguish
developer/local/lab runs from protected CI: change "Integration tests are
allowed but MUST be clearly marked and skippable in CI." to language that
permits tests to be skippable during local or iterative CI lanes but requires
integration test coverage in protected workflows (e.g., required pre-merge
check, nightly job, or separate required lane) as referenced by Lines 45–49;
ensure the new wording mandates clear marking and a mechanism to skip in
non-protective runs while explicitly requiring execution in the protected CI
gates.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Claude
AI
changed the title
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (1)
AGENTS.md (1)
56-60:⚠️ Potential issue | 🟡 MinorFix fenced-code spacing to satisfy markdownlint (MD031).
Add blank lines before and after the fenced block around the GraphQL command example. This issue was previously flagged and remains unresolved.
Markdownlint-compliant patch
- Use the GitHub GraphQL API via `gh api graphql` with the `resolveReviewThread` mutation: + ```bash gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "PRRT_..."}) { thread { id isResolved } } }'
- Retrieve thread IDs first with a
reviewThreadsquery on the pull request.</details> <details> <summary>🤖 Prompt for AI Agents</summary>Verify each finding against the current code and only fix it if needed.
In
@AGENTS.mdaround lines 56 - 60, The fenced code block containing the GraphQL
example (the triple-backtick block around the gh api graphql -f query='mutation
{ resolveReviewThread(... ) }' example) needs blank lines before and after the
opening and closingto satisfy markdownlint MD031; edit AGENTS.md to insert an empty line immediately above the openingand an empty line immediately
below the closing ```, ensuring the surrounding sentence ("Use the GitHub
GraphQL API..." and "Retrieve thread IDs first...") are separated from the
fenced block.</details> </blockquote></details> </blockquote></details> <details> <summary>🤖 Prompt for all review comments with AI agents</summary>Verify each finding against the current code and only fix it if needed.
Inline comments:
In@AGENTS.md:
- Line 28: Clarify that the “4. Tests — run the full test suite with
coverage” instruction is a pre-commit requirement by appending a short
parenthetical (e.g., “(required before committing/pushing)”), and update the
guidance that currently reads about running “specific tests rather than the full
suite when iterating” to explicitly call out that this is an iterative/dev-loop
recommendation (e.g., “(recommended during local iteration to save time; run
full suite before commit)”). Locate and edit the two exact strings "4. Tests
— run the full test suite with coverage" and "specific tests rather than the
full suite when iterating" to add the clarifying parentheticals so readers can
easily distinguish pre-commit vs iterative expectations.
Duplicate comments:
In@AGENTS.md:
- Around line 56-60: The fenced code block containing the GraphQL example (the
triple-backtick block around the gh api graphql -f query='mutation {
resolveReviewThread(... ) }' example) needs blank lines before and after the
opening and closingto satisfy markdownlint MD031; edit AGENTS.md to insert an empty line immediately above the openingand an empty line immediately
below the closing ```, ensuring the surrounding sentence ("Use the GitHub
GraphQL API..." and "Retrieve thread IDs first...") are separated from the
fenced block.</details> <details> <summary>🪄 Autofix (Beta)</summary> Fix all unresolved CodeRabbit comments on this PR: - [ ] <!-- {"checkboxId": "4b0d0e0a-96d7-4f10-b296-3a18ea78f0b9"} --> Push a commit to this branch (recommended) - [ ] <!-- {"checkboxId": "ff5b1114-7d8c-49e6-8ac1-43f82af23a33"} --> Create a new PR with the fixes </details> --- <details> <summary>ℹ️ Review info</summary> <details> <summary>⚙️ Run configuration</summary> **Configuration used**: Organization UI **Review profile**: ASSERTIVE **Plan**: Pro **Run ID**: `5b74a978-6e67-4e00-b393-25d399871fae` </details> <details> <summary>📥 Commits</summary> Reviewing files that changed from the base of the PR and between 95b3feb9d985f81c1f14018da7e73baaadfa690d and f280f532313c484a65ffefad3d53ad277ed8ccd9. </details> <details> <summary>📒 Files selected for processing (1)</summary> * `AGENTS.md` </details> </details> <!-- This is an auto-generated comment by CodeRabbit for review status -->
- Replace brief planning artifacts section with prescriptive BMAD Method section: mandatory installation, required SDD workflow, planning artifact requirements, agent usage, and readiness validation - Add comprehensive CI Quality Gates section listing all required checks: CodeQL, SonarCloud, CodeRabbit, GitHub Copilot, linting, formatting, type checking, tests, and code coverage - Remove old generic CI section (now incorporated into new section) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
♻️ Duplicate comments (3)
AGENTS.md (3)
46-50:⚠️ Potential issue | 🟡 MinorFix markdownlint MD031 around the GraphQL fenced block.
Line 47 and Line 49 still violate fenced-block spacing in this list section. Add a blank line before and after the fenced block.
Patch
- Use the GitHub GraphQL API via `gh api graphql` with the `resolveReviewThread` mutation: + ```bash gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "PRRT_..."}) { thread { id isResolved } } }'
- Retrieve thread IDs first with a
reviewThreadsquery on the pull request.</details> <details> <summary>🤖 Prompt for AI Agents</summary>Verify each finding against the current code and only fix it if needed.
In
@AGENTS.mdaround lines 46 - 50, The markdown fenced code block starting withbefore the ```bash fence and another blank line immediately after the closing ``` fence so the code block is separated from the surrounding list item text (ensure the `gh api graphql` example block is surrounded by one empty line above and below).
16-16:⚠️ Potential issue | 🟠 MajorTighten integration-test CI policy to require a protected gate.
Line 16 says CI must always run integration tests, but the “scheduled workflow” example can bypass pre-merge protection. Require execution in at least one protected workflow.
Patch
-- Integration tests are allowed but MUST be clearly marked. They may be skipped locally during rapid iteration, but CI MUST always run them (for example, in a separate job or scheduled workflow). +- Integration tests are allowed but MUST be clearly marked. They may be skipped locally during rapid iteration, but MUST run in at least one protected CI workflow (for example, a required pre-merge job; optionally also in a scheduled workflow).🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@AGENTS.md` at line 16, Update the integration-test policy sentence (the line currently stating "CI MUST always run them (for example, in a separate job or scheduled workflow)") to require execution in at least one protected workflow; change it to say CI MUST always run integration tests and at least one must be enforced by a protected/required workflow (e.g., a required pre-merge job or branch protection check), while allowing additional scheduled workflows for periodic runs or local skips. Ensure the wording replaces the current parenthetical example and explicitly mentions "protected/required workflow" or "required pre-merge job" so the policy cannot be satisfied by only a scheduled workflow.
28-28:⚠️ Potential issue | 🟡 MinorClarify pre-commit full-suite requirement vs iterative test guidance.
Line 28 and Line 140 still read as potentially conflicting. Add explicit parentheticals to distinguish required pre-commit behavior from local iteration advice.
Patch
-4. **Tests** — run the full test suite with coverage +4. **Tests** — run the full test suite with coverage (required before committing/pushing) -- Prefer small, focused commands — run specific tests rather than the full suite when iterating. +- Prefer small, focused commands — run specific tests rather than the full suite when iterating (recommended during local iteration; run full suite before commit).Also applies to: 140-140
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@AGENTS.md` at line 28, Update the two ambiguous test instructions that currently read like "4. **Tests** — run the full test suite with coverage" (line showing the numbered Tests item) and the corresponding line at 140 to explicitly distinguish required pre-commit behavior from local iterative guidance by adding parentheticals: change the pre-commit/required instance to include "(required before committing/pushing; full test suite with coverage)" and change the local iteration instance to include "(optional during local development; run targeted tests for faster feedback)"; ensure these exact phrases are applied to the two occurrences so readers clearly understand which is mandatory and which is advisory.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Duplicate comments:
In `@AGENTS.md`:
- Around line 46-50: The markdown fenced code block starting with ```bash in
AGENTS.md violates MD031; fix it by adding a blank line immediately before the
```bash fence and another blank line immediately after the closing ``` fence so
the code block is separated from the surrounding list item text (ensure the `gh
api graphql` example block is surrounded by one empty line above and below).
- Line 16: Update the integration-test policy sentence (the line currently
stating "CI MUST always run them (for example, in a separate job or scheduled
workflow)") to require execution in at least one protected workflow; change it
to say CI MUST always run integration tests and at least one must be enforced by
a protected/required workflow (e.g., a required pre-merge job or branch
protection check), while allowing additional scheduled workflows for periodic
runs or local skips. Ensure the wording replaces the current parenthetical
example and explicitly mentions "protected/required workflow" or "required
pre-merge job" so the policy cannot be satisfied by only a scheduled workflow.
- Line 28: Update the two ambiguous test instructions that currently read like
"4. **Tests** — run the full test suite with coverage" (line showing the
numbered Tests item) and the corresponding line at 140 to explicitly distinguish
required pre-commit behavior from local iterative guidance by adding
parentheticals: change the pre-commit/required instance to include "(required
before committing/pushing; full test suite with coverage)" and change the local
iteration instance to include "(optional during local development; run targeted
tests for faster feedback)"; ensure these exact phrases are applied to the two
occurrences so readers clearly understand which is mandatory and which is
advisory.
- Add blank lines around fenced code block in PR Reviews section (MD031) - Clarify pre-commit vs iteration test requirements with cross-references between Pre-Commit Quality Checks and Agent Operation Guidance Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@AGENTS.md`:
- Line 131: Replace the casual phrase "fix the issue" in the sentence "If any
check fails in CI, investigate locally, fix the issue, and re-run" with a more
formal verb such as "resolve," "address," or "correct" (e.g., "resolve the
issue") to improve tone while keeping meaning and flow; update the sentence
accordingly where that exact phrase appears.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
| - All checks above are configured as **required status checks** on the default branch. | ||
| - **Iterate until all CI checks pass.** Before requesting review or marking a PR as ready: | ||
| - Run all checks locally (format, lint, typecheck, tests, coverage) | ||
| - If any check fails in CI, investigate locally, fix the issue, and re-run |
There was a problem hiding this comment.
🧹 Nitpick | 🔵 Trivial
Optional: Consider more formal verb (purely stylistic).
LanguageTool suggests replacing "fix the issue" with a more formal verb like "resolve," "address," or "correct." However, "fix" is widely accepted and clear in technical documentation, so this change is entirely optional.
♻️ Optional stylistic refinement
- - If any check fails in CI, investigate locally, fix the issue, and re-run
+ - If any check fails in CI, investigate locally, resolve the issue, and re-run📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| - If any check fails in CI, investigate locally, fix the issue, and re-run | |
| - If any check fails in CI, investigate locally, resolve the issue, and re-run |
🧰 Tools
🪛 LanguageTool
[style] ~131-~131: Consider using a different verb for a more formal wording.
Context: ...check fails in CI, investigate locally, fix the issue, and re-run - Continue iter...
(FIX_RESOLVE)
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed.
In `@AGENTS.md` at line 131, Replace the casual phrase "fix the issue" in the
sentence "If any check fails in CI, investigate locally, fix the issue, and
re-run" with a more formal verb such as "resolve," "address," or "correct"
(e.g., "resolve the issue") to improve tone while keeping meaning and flow;
update the sentence accordingly where that exact phrase appears.
This was referenced Mar 28, 2026
This was referenced Apr 5, 2026
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 by CodeRabbit