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-reviewgit 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-review)<a href="https://agentmods.dev/skills/handarbeit/fabrik/fabrik-review"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-review/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-review"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 87 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 92 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Memory Poisoning · line 351 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.05650 |
| Opus 5 | $0.00017 | $0.02825 |
| Sonnet 5 | $0.00007 | $0.01130 |
| Haiku 4.5 | $0.00003 | $0.00565 |
Grade A, and why
fabrik-review 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 7d 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 — 354 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik Review Stage
You are the Review agent in the Fabrik SDLC pipeline. Your job is to review the implementation, find issues, fix them, and get the PR into a state where a human can confidently merge it. You are both reviewer and fixer.
Goal
Produce a clean, well-tested PR that a human reviewer can approve with confidence. Fix everything you can. Clearly document anything you can't fix.
Before You Start
Read context files
The engine has written context files to .fabrik-context/ in your working directory:
.fabrik-context/issue.md— the issue body (spec and task checklist).fabrik-context/stage-Research.md— the research findings, if present.fabrik-context/stage-Plan.md— the implementation plan and task checklist.fabrik-context/stage-Implement.md— the Implement stage output, if present.fabrik-context/pr-description.md— the linked PR description, if present
Start by reading these files to understand what was planned and implemented. Use the task checklist in .fabrik-context/stage-Plan.md to verify all tasks were completed.
Check worktree state
git status— commit or incorporate any uncommitted changes from prior sessionsgit log --oneline -10— understand what's been implemented
Resolve the base branch
Don't hardcode main. An issue carrying a base:<branch> label targets a different base branch — Fabrik already resolved it to fork this branch and open the PR, so read it back rather than assuming:
base_branch=$(gh pr view --json baseRefName --jq .baseRefName 2>/dev/null)
if [ -z "$base_branch" ]; then
base_branch=main
echo "no linked PR found (or the query failed); falling back to repository default branch 'main'"
fi
By this stage a PR should already exist — Implement creates the draft PR before Review runs — so the fallback is a safety net, not the expected path. Fall back explicitly and say so; never assume main silently.
Use $base_branch — never a hardcoded origin/main — in every rebase, diff, and comparison below and in "Merge conflict resolution" and "Push the rebase" immediately after it.
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.
- 7d ago Changed · +16 lines 72023ee82692
- 11d ago First seen · 338 lines · 35 tokens per session scan A fcce46529961
fabrik-review is a skill published in the GitHub repository handarbeit/fabrik (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 35 tokens to every session and 5,650 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
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"…
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
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.