Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/edutrul/drupal-ai/code-reviewgit clone --depth 1 https://github.com/edutrul/drupal-aiWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00063 | $0.01208 |
| Opus 5 | $0.00032 | $0.00604 |
| Sonnet 5 | $0.00013 | $0.00242 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Run a full code review against changed files — static analysis, PHPCS, PHPStan, and best-practice checks.
Purpose
Use this command to review work before a PR or during a PR — whether you have a Jira ticket, a branch name, a PR number, or nothing at all.
Input
Optional. One of:
- Jira ticket ID — e.g.
TICKET-123 - Branch name — e.g.
my-feature-branch - PR number — e.g.
612or#612 - Nothing → defaults to current branch
Step 1 — Resolve input to a branch
No input
git branch --show-current
Use the result as the branch.
Jira ticket (e.g. TICKET-123)
gh pr list --search "TICKET-123" --json number,headRefName,title
If a PR is found → use its branch. If no PR → search local/remote branches for the ticket ID:
git branch -a | grep -i TICKET-123
Use the first match. If nothing found → tell the user and stop.
PR number (e.g. 612)
gh pr view 612 --json headRefName,title,files
Use the headRefName as the branch.
Branch name
Use it directly. Verify it exists:
git fetch origin
git log origin/<branch> -1
If not found → tell the user and stop.
Step 2 — Get changed files
Get the diff between the resolved branch and the base branch (as defined in workflow.md — typically develop or main):
git fetch origin
git diff origin/<base-branch>...origin/<branch> --name-only
If on current branch (no remote yet):
git diff origin/<base-branch>...HEAD --name-only
Show the list of changed files to the user.
If no changed files → tell the user and stop.
Step 3 — Run PHPCS on changed PHP files
Filter changed files to those in PHPCS scope:
docroot/modules/custom/docroot/themes/custom/docroot/sites/default/settings.php
For each matching file, run:
phpcs <file-path>
Collect all output. Store raw results — use them as-is in the report.
If no in-scope PHP files → note "PHPCS: no in-scope files" and skip.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 211 lines · 63 tokens per session scan A f0e3e2c0c272
code-review is a command published in the GitHub repository edutrul/drupal-ai (71 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 1,208 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
config
Command "config" from sdebruyn/fabric-dw-mcp-cli, covering configuration & defaults, http retry budget, sql retry budget, mcp workspace allowlist {#mcp-workspace-allowlist} and mcp server log level.
deps-age
Analyze dependency freshness and maintenance activity.