Borrowing it
Nothing to install: this file belongs to appclawhq/AppClaw. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/appclawhq/AppClaw/main/.agents/skills/review-changes/SKILL.mdgit clone --depth 1 https://github.com/appclawhq/AppClawWrote 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/appclawhq/appclaw/review-changes)<a href="https://agentmods.dev/skills/appclawhq/appclaw/review-changes"><img src="https://agentmods.dev/badge/skills/appclawhq/appclaw/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/appclawhq/appclaw/review-changes"><img src="https://agentmods.dev/badge/skills/appclawhq/appclaw/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 | $0.00104 | $0.01366 |
| Opus 5.5 | $0.00042 | $0.00546 |
| Sonnet 5.5 | $0.00021 | $0.00273 |
| Haiku 4.5 | $0.00010 | $0.00137 |
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 2mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Changes
This skill reviews code changes in AppClaw to catch breakage across two surfaces (CLI and VSCode extension) and validate YAML flow parsing. AppClaw has a fragile contract between these surfaces — the CLI emits NDJSON events that the extension parses, and changes to either side can silently break the other.
Why this matters
AppClaw has three main failure modes when code changes:
- CLI ↔ Extension drift — The CLI's
src/json-emitter.tsdefines event types. The extension'svscode-extension/src/bridge.tsmirrors those types manually. When someone adds a field to one side, the other silently ignores it, causing subtle bugs. - YAML flow parsing regressions — Natural language parsing in
src/flow/natural-line.tsuses regex patterns that interact in surprising ways. A change to one regex can break another flow format. - Config drift — The CLI reads env vars via
src/config.ts(Zod schema). The extension maps VS Code settings to env vars inbridge.ts:getEnvFromSettings(). New config options added to one side may not appear in the other.
Review process
When triggered, perform these checks in order:
Step 1: Identify what changed
Run git diff (staged + unstaged) and git diff --cached to see all pending changes. Categorize the changed files:
- Shared contract files (high risk):
src/json-emitter.ts,src/flow/types.ts,src/config.ts - CLI-side flow files (medium risk):
src/flow/natural-line.ts,src/flow/parse-yaml-flow.ts,src/flow/run-yaml-flow.ts,src/flow/variable-resolver.ts,src/flow/llm-parser.ts - Extension files (medium risk): anything under
vscode-extension/src/ - Other files (lower risk): agent, perception, vision, etc.
Step 2: Cross-surface consistency check
If any shared contract files changed, or if extension/CLI files changed:
Event type check:
- Read
src/json-emitter.ts(theJsonEventtype union) - Read
vscode-extension/src/bridge.ts(theAppclawEventtype and individual event interfaces) - Compare every event variant — field names, types, optional vs required
- Flag any mismatch (missing fields, type differences, new events not mirrored)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 135 lines · 104 tokens per session scan A 349899bed9f7
review-changes is a skill published in the GitHub repository appclawhq/AppClaw (120 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 1,366 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
engineer-bot-getting-started
An onboarding guide for an engineering delivery assistant. It helps define a repository, the allowed level of access, and the work needed before reviewing a code change.
nightly-audit-engineer-getting-started
A first-conversation guide for setting up a code-audit assistant. A code audit is a focused review of source code for defects or risky behavior, with the needed repository, scope, concerns, permissions, and schedule clarified first.
mobile-automation
Control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take screenshots, read the accessibility tree. Use when a task involves a mobile device or app, mobile UI testing, or reproducing a bug on a phone.
nightly-audit-engineer-ops
A workflow for reviewing code for reproducible quality problems and recording the evidence behind each finding. It follows data through inputs, permissions, storage, asynchronous work, and recovery, then suggests the smallest authorized fix.
engineer-bot-evidence
A local checker for confirming that delivery checks and supporting evidence belong to the current software version. It does not contact Git, continuous-integration systems, or the internet.
nightly-audit-engineer-evidence
A small local checker that creates stable identifiers for code-audit findings and marks duplicates within the current batch or among previously seen findings. It processes supplied JSON with Python and does not infer whether a problem was fixed.