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 skills/matheuspavaneli/workbench/review-diffnpx skills add matheusPavaneli/workbench --skill review-diffgit clone --depth 1 https://github.com/matheusPavaneli/workbenchWhat 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 | $0.00043 | $0.00679 |
| Opus 5 | $0.00022 | $0.00340 |
| Sonnet 5 | $0.00009 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
review-diff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-diff
python "${CLAUDE_PLUGIN_ROOT}/lib/wb.py" <args>
Steps
-
Get the computed facts.
review context(add--stagedfor the staged diff). It reports the preset, every changed file, the critical zones touched, the sources that changed with no test alongside, and the gates that apply. -
Read the diff itself, then read the surrounding code. A diff shows what changed, not what it broke. For anything that changes a shared contract, ask the index who calls it:
${CLAUDE_PLUGIN_ROOT}/shared/code-search.md. -
Settle the mechanical gates first.
review gates(add--key <KEY>so the bug-fix regression rule knows the ticket type). It reads the added lines and reports secrets, swallowed errors and added dependencies asfile:linefindings. Exit 7 means it found some; report them, do not re-derive them. A dependency finding is a question to answer, not a defect: say who owns it and why nothing already in the repo does the job. -
Check the rest of the gates yourself. Every gate
review contextprinted thatreview gatesdid not settle is a question with a yes or no answer for this diff. The floor is not negotiable at any preset: unit test for changed logic, regression test with a bug fix, no swallowed error, no secret, a stated rollback. -
Go deeper in critical zones. Billing, auth, user data, migrations and secrets are held to a higher standard than the preset otherwise sets. In those files, read every changed line and its error path.
-
Report findings, most severe first:
path/to/file.py:42 high Coupon is validated after the charge is created. An expired coupon charges the card, then errors.Severity: high — wrong behaviour, data loss, or a security hole. medium — will break under a plausible input or state. low — real but contained. Skip formatting and taste unless it changes meaning.
-
Say when it is clean. "No findings" is a result. Do not manufacture a finding to look thorough.
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.
- yesterday First seen · 64 lines · 43 tokens per session scan A 1182f07e8765
review-diff is a skill published in the GitHub repository matheusPavaneli/workbench (1 stars, last pushed 10d ago), licensed MIT. It adds 43 tokens to every session and 679 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
integration-rule-engine
A declarative routing engine that turns ticket / error attributes (reporter, label, project, area path, error class, environment) into a tag + AI agent + priority assignment, so cross-source workflows ("security tickets always go to the OWASP reviewer") stay out of code and in user-editable rules.
stale-ticket-triage
Replace the weekly "look at every ticket older than X days" meeting with a scheduled AI scan that picks close / snooze / keep per ticket plus a one-sentence reason, so a PM can bulk-approve in 90 seconds Monday morning.
azure-devops
Manage Azure DevOps projects, work items, repos, PRs, pipelines, wikis, test plans, security alerts, variable groups, environments/approvals, branch policies, and attachments. Use when user asks to: manage sprints, create/update work items, list repos, create PRs, run pipelines, search code, manage wiki pages, check…
apple-container
Apple's open-source container CLI to build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS — no Docker daemon required. Use when the user mentions the container CLI, "apple container", running or building containers on macOS without Docker/Podman, container run, container…
atlassian
Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…
google-calendar
Interact with Google Calendar - list calendars, view events, create/update/delete events, and find free time. Use when user asks to: check calendar, schedule a meeting, create an event, find available time, list upcoming events, delete or update a calendar event, or respond to meeting invitations. Lightweight…