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 juspay/xyne-spaces --skill review-changesgit clone --depth 1 https://github.com/juspay/xyne-spacesWrote 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/juspay/xyne-spaces/review-changes)<a href="https://agentmods.dev/skills/juspay/xyne-spaces/review-changes"><img src="https://agentmods.dev/badge/skills/juspay/xyne-spaces/review-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/juspay/xyne-spaces/review-changes"><img src="https://agentmods.dev/badge/skills/juspay/xyne-spaces/review-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 | $0.00035 | $0.01927 |
| Opus 5.5 | $0.00014 | $0.00771 |
| Sonnet 5.5 | $0.00007 | $0.00385 |
| Haiku 4.5 | $0.00003 | $0.00193 |
Grade A, and why
Review 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 27d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing a change set
Use this skill when the user asks for a review of code changes, or asks to be walked through what changed and why.
Two intents, one gathering step
Read the intent from the user's own words.
- Critique — "review this", "what's wrong", "is this safe". Judge the change.
- Teach — "explain this", "walk me through", "teach me". Describe the change so someone new can follow it.
The gathering work below is identical for both. Only the write-up differs. When the intent is genuinely unclear, critique, and offer the walkthrough at the end in one line.
Cover every file, provably
Before reading anything, list the changed files with git. That list, not your memory of the diff, is the scope.
Walk it in order. Every file ends in one of two states, and both are recorded in coverage:
- reviewed — you read that file's diff.
- skipped — you chose not to, with a one-line reason. Legitimate reasons: generated output, a lockfile, a binary, a pure formatting pass, a vendored directory. "Large" is not a reason. "Looked unrelated" is not a reason.
The viewer compares your coverage against the real file list and shows the user precisely which files you left out, so silence is not an option and an omission is not deniable. A large change means working through it in batches, not stopping early.
Gather before you judge
- Establish the scope. Uncommitted work, a branch against its base, or a named set of files. Ask only if the answer changes what you read.
- Read the diff in full. Never review a summary of a diff.
- Open the surrounding code for anything you intend to criticise. A hunk alone rarely proves a defect.
- Follow the data. When a value is produced in one file and consumed in another, read both ends. Fields dropped between layers are invisible in a single-file view and are among the most common real defects.
- Note what is missing: tests for new behaviour, error paths, and callers that were not updated.
Judging
Rank by what breaks, not by what is easy to spot.
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.
- 27d ago First seen · 133 lines · 35 tokens per session scan A a02d128be3fd
Review Changes is a skill published in the GitHub repository juspay/xyne-spaces (807 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,927 once invoked, about $0.0001 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 2026-09-19.
Other skills, from other repositories
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…
triage
Triages a PR comment — from a bot (Copilot, CI) or a human reviewer. Routes to the triagehelper.py helper for identity checks, thread snapshotting, isolated-worktree fixes, and publish/reply/resolve mechanics; you classify the finding and apply a justified fix. --dry-run is fully read-only (investigation and a printed…
review
The vendor review chain the loop skills run and never the model itself — code-review.ts over a git diff, spec-audit.ts over a SPEC or spec folder, policy-review.ts over any artifact — each walking a row of the policy table (policy.json here: Codex first, its declared backup next, never the vendor that wrote the code…
git-workflow
Git workflow and conventional commits. Use when working with git, branches, commits, pull requests, code review, or version control strategy.
gh-address-comments
Triage and address open GitHub PR review and conversation comments using the gh CLI. Use when the user wants to "address PR comments", "resolve review threads", or "respond to reviewers" on the current branch's pull request.
pr-sweep
Use when you want to sweep all open pull requests across all repos, triage their status, run code reviews on unreviewed PRs, merge what's ready, fix quick blockers, and produce a full status report. Trigger when the user says "check my PRs", "close out open PRs", "what's the status of my PRs", "sweep my PRs", "PR…