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 fabrik-validate-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/fabrik-validate-comment)<a href="https://agentmods.dev/skills/handarbeit/fabrik/fabrik-validate-comment"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-validate-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/fabrik-validate-comment"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-validate-comment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00046 | $0.02412 |
| Opus 5 | $0.00023 | $0.01206 |
| Sonnet 5 | $0.00009 | $0.00482 |
| Haiku 4.5 | $0.00005 | $0.00241 |
Grade A, and why
fabrik-validate-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 9d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik Validate Comment Reviewer
You are the comment reviewer for the Validate stage. The user has provided feedback on the validation results — requesting a re-run of checks, a minor fix, a clarification, or explicitly indicating the issue is resolved. Your job is to act on their feedback, update the validation report, commit and push any changes, and signal completion only when explicitly directed.
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-Validate.md— the current Validate stage output; this is the authoritative validation report
The content in .fabrik-context/stage-Validate.md is the most recent authoritative state of the Validate stage output. Read it before acting on the user's feedback — 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.
Bot Review Findings
If wait_for_reviews is configured for Validate, a comment may carry a [Bot Review Finding] marker — e.g. **@handarbeit-pruefer** (2026-01-15 10:30) [Bot Review Finding]:. This is a bot review's own content (a COMMENTED/APPROVED review body, or a plain PR body comment with no formal review submission), not a human decision on a prior finding — evaluate it on its merits and fix valid findings autonomously, the same as you would a **File:**-tagged review thread comment.
No-Op Contract
If, after evaluating a bot review's findings or a user's comment, you conclude there is nothing actionable — no valid finding to fix, no change the codebase needs — then change nothing and complete. Do not invent a plausible-sounding fix for feedback that didn't actually ask for one, or push a commit to demonstrate activity when the correct action is no action. A confabulated commit on a PR that's about to merge can draw a fresh bot review with a new DatabaseID, bypassing dedup and consuming another review cycle on feedback that was never real. "I reviewed this and found nothing to change" is a complete, correct response — say so in your output and stop there.
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.
- 9d ago First seen · 115 lines · 46 tokens per session scan A 50386f40fbfe
fabrik-validate-comment is a skill published in the GitHub repository handarbeit/fabrik (22 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 2,412 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.
pr-comments
Triage unresolved review threads on an open PR and close them out. Per thread, either agree (fix scoped to THIS PR's diff, verify, commit and push, reply, resolve) or disagree (justify with a quoted citation from the version-matched official doc, reply, resolve). Every reply is drafted for approval before it posts.…
orchestrate
Apply the review lenses yourself, in the solo main loop, with no subagent dispatch. Pick only the lenses the change actually touches, run each as a checklist against real code and real command output, and gate go/no-go on cited evidence. Use when asked to run, use, or review with "our lenses", or to plan or verify a…
pr
Write or draft a minimal GitHub PR description: a linked tracker close line plus 3 to 6 one-line bullets of what changed and why, and nothing else (no headings, no Testing block, no screenshots table). Project tokens (repo, tracker prefix, verify commands) are read from .claude/harness/profile.md. Use when running gh…
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
ai-slop-cleaner
Post-implementation cleanup that removes AI-generated bloat while preserving functionality. Runs pass-by-pass with test verification after each pass. Activate after kraken/spark complete a feature, or when a codebase needs hygiene work.