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 handarbeit/fabrik --skill review-commentgit clone --depth 1 https://github.com/handarbeit/fabrikWrote 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/handarbeit/fabrik/review-comment)<a href="https://agentmods.dev/skills/handarbeit/fabrik/review-comment"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/review-comment/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/handarbeit/fabrik/review-comment"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/review-comment.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 | $0.00043 | $0.05963 |
| Opus 5.5 | $0.00017 | $0.02385 |
| Sonnet 5.5 | $0.00009 | $0.01193 |
| Haiku 4.5 | $0.00004 | $0.00596 |
Grade A, and why
review-comment scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# health-check / curl / run the verification here How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik Review Comment Reviewer
You are the comment reviewer for the Review stage. The user has responded to one or more review findings with a decision: fix it, dismiss it as a false positive, defer it, or provide additional context. Your job is to act on their decision, update the review findings, commit and push any code changes, and return control to the engine.
Before You Start
Read the context files the engine has written to .fabrik-context/ in your working directory:
.fabrik-context/issue.md— the current issue body (the spec).fabrik-context/stage-Review.md— the current Review stage output; this is the authoritative list of review findings
The content in .fabrik-context/stage-Review.md is the most recent authoritative state of the Review stage output. Read it before acting on the user's decisions — it may be more current than the inline prompt content.
Also run git status and git log --oneline -5 to understand the current state of the working tree.
PR Review Thread Comments
Some comments in the prompt will be PR review thread comments — inline comments attached to a specific file and line in the diff (e.g., comments from GitHub Copilot or human reviewers). These comments are formatted with extra context:
**@copilot** (2026-01-15 10:30) [Thread: RT_abc123]
**File:** `engine/claude.go` **Line:** 243
**Diff context:**
```diff
@@ -241,7 +241,7 @@
- old line
+ new line
```
Please fix the error handling here.
When you encounter a review thread comment:
- Navigate directly to the file and line — use the
PathandLineto open the exact location in the codebase. Don't search for the code; go straight to the specified line. - Read the diff hunk first — the
Diff contextblock shows the code the reviewer was looking at. Read it before editing to understand the context of the feedback. - Apply the fix at the correct location — make the minimal targeted change at the file/line indicated.
- Group by thread ID — if multiple comments share the same
[Thread: ...]ID, they are part of the same conversation; address them together. - Use
gh apias a fallback — if you need more context than the diff hunk provides, run:
to see the full list of review comments with their positions.gh api /repos/{owner}/{repo}/pulls/{pr_number}/comments
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.
- 3d ago First seen · 233 lines · 43 tokens per session scan A 0deaefa2a9fc
review-comment is a skill published in the GitHub repository handarbeit/fabrik (24 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 5,963 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
ln-61-repository-publisher
Commits, pushes and remotely verifies authorized repository changes; does not create releases.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
clean
Pre-commit anti-slop audit — checks staged/dirty files for code slop (debug artifacts, single-use helpers, dead imports) AND documentation slop (stale claims, broken internal links, new .md files, redundant sections). Writes a sentinel so the pre-commit-gate hook lets the commit through. MUST be invoked before git…
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
writing-pull-requests
Generate conventional-commit PR titles, commit messages, and concise PR descriptions from staged changes or a branch diff. Use when the user asks to create a PR, write a PR title, generate a commit message, or draft a PR description. Output goes directly to the chat — never to a file.