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 skills add tomzx/agents --skill review-sdk-changesgit clone --depth 1 https://github.com/tomzx/agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/tomzx/agents/review-sdk-changes)<a href="https://agentmods.dev/skills/tomzx/agents/review-sdk-changes"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-sdk-changes/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/tomzx/agents/review-sdk-changes"><img src="https://agentmods.dev/badge/skills/tomzx/agents/review-sdk-changes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00087 | $0.04736 |
| Opus 5.5 | $0.00035 | $0.01894 |
| Sonnet 5.5 | $0.00017 | $0.00947 |
| Haiku 4.5 | $0.00009 | $0.00474 |
Grade A, and why
review-sdk-changes 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 6d 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 — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review SDK Changes
Reviews a change to a published client library or SDK and reports findings. It answers one question: does this change treat the SDK's consumers well? Covering breaking changes to the public surface, versioning and release, ergonomics, type safety, error handling, configuration, pagination, packaging, dependencies, and documentation.
An SDK is consumed by code the author cannot change, so every public symbol is a contract.
The review is therefore biased toward compatibility: a change that is correct in isolation can still be a 🔴 MUST if it silently breaks a caller.
It is the change-time companion to /review-pr, which keeps general code craft, and to /review-api-changes, which reviews the wire contract the SDK wraps.
This review is static: it does not build or run the SDK, so behavior observed by running it is /verify-pr's to prove.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md(PR Review Reports for report location and posting rules). - Apply the shared evidence standard in
../sdlc/references/evidence.md. Static claims carryL1 - CitedorL2 - Ruled out; a decisive claim proven by a read-only command can reachL3 - Executed. - The change to review, in one of these forms:
- a PR number plus repository (
/review-sdk-changes 42 acme/sdk-python), - a git diff ref (for example
origin/main..HEAD), - a worktree directory, or a changeset already in context.
- a PR number plus repository (
- The public surface at the base revision, so before/after can be compared. Read it from the package entry point and its exports rather than from the diff alone.
- The SDK's packaging metadata (manifest, entry points, exports map, type declarations) and current version.
- The generated-code source when the SDK is generated (for example an OpenAPI spec), to check regeneration drift.
Skill attribution (GitHub)
Before posting to GitHub, read ../github-post-attribution/SKILL.md and append the footer for SKILL_DIR = review-sdk-changes.
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.
- 6d ago Changed · -2 lines be1372a92413
- 9d ago Changed · +12 lines 99ea88496040
- 11d ago First seen · 381 lines · 87 tokens per session scan A 3cab12303e1f
review-sdk-changes is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 4,736 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-19.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…