Skip to content

[caveman] Optimize instruction verbosity — adr-writer, contribution-checker (2026-07-03) #43266

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pelikhan merged 1 commit into from
Jul 4, 2026
+11 −24
Merged

[caveman] Optimize instruction verbosity — adr-writer, contribution-checker (2026-07-03) #43266

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 4 additions & 13 deletions .github/agents/adr-writer.agent.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,20 +82,11 @@ Example: `docs/adr/0001-use-postgresql-for-primary-storage.md`

## Writing Quality Standards

#### Context (3–5 sentences)
- Problem and constraints (technical, organizational, timeline)
- Codebase state at decision time; problem space, not implementation
Beyond the per-section length hints in the template:

#### Decision (2–4 sentences)
- Active voice: "We will use X because Y"
- Name primary driver (performance, simplicity, cost) and pattern/principle if applicable

#### Alternatives Considered (2–4 sentences each)
- **≥2 genuine alternatives** (no strawmen); for each: what, why considered, why rejected

#### Consequences
- **Positive**, **Negative**, **Neutral**: real benefits, costs, and side effects
- ≥2 per category for non-trivial decisions
- **Decision** — active voice ("We will use X because Y"); name the primary driver (performance, simplicity, cost).
- **Alternatives** — ≥2 genuine options, no strawmen; each: what, why considered, why rejected.
- **Consequences** — ≥2 per Positive/Negative/Neutral category for non-trivial decisions.

## Procedure: Writing a New ADR

Expand Down
18 changes: 7 additions & 11 deletions .github/agents/contribution-checker.agent.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,17 +85,13 @@ Return a single **JSON object** (no extra text):
}
```

Where:
- `verdict` is one of: `🔴`, `⚠️`, `🟡`, `🟢`, `❓`
- `on_topic` is `yes`, `no`, or `unclear`
- `focused` is `yes` or `no`
- `deps` is `yes` or `no`
- `tests` is `yes` or `no`
- `lines` is the total lines changed (integer)
- `quality` is one of: `spam`, `needs-work`, `lgtm`, `no-guidelines`
- `existing_labels` is an array of the PR's current labels, or `[]` if none
- `title` is the PR title
- `author` is the PR author's username
Field values:
- `verdict`: `🔴`, `⚠️`, `🟡`, `🟢`, or `❓`
- `on_topic`: `yes`, `no`, or `unclear`
- `focused`, `deps`, `tests`: `yes` or `no`
- `lines`: total lines changed (integer)
- `quality`: `spam`, `needs-work`, `lgtm`, or `no-guidelines`
- `existing_labels`: array of the PR's current labels, or `[]`

### Comment Field

Expand Down
Loading