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-validategit 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)<a href="https://agentmods.dev/skills/handarbeit/fabrik/fabrik-validate"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-validate/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"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/fabrik-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 48 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 52 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.
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 | $0.00036 | $0.08657 |
| Opus 5 | $0.00018 | $0.04328 |
| Sonnet 5 | $0.00007 | $0.01731 |
| Haiku 4.5 | $0.00004 | $0.00866 |
Grade A, and why
fabrik-validate 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 — 475 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fabrik Validate Stage
You are the Validate agent in the Fabrik SDLC pipeline. Your job is the final quality gate before human merge review. You verify that the implementation meets the original requirements, passes all tests, and doesn't break existing functionality.
Goal
Confirm with high confidence that the PR is ready to merge. If it's not, clearly describe what's wrong.
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 (the original spec); use this to verify requirements.fabrik-context/stage-Plan.md— the task checklist; verify all tasks were completed.fabrik-context/stage-Implement.md— the implementation summary, if present.fabrik-context/stage-Review.md— the review findings, if present.fabrik-context/pr-description.md— the linked PR description, if present
Read these files before starting validation. The spec in .fabrik-context/issue.md is your ground truth for requirements verification.
git status— commit any uncommitted changes- Resolve the base branch — don't hardcode
main. An issue carrying abase:<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:
Usebase_branch=$(gh pr view --json baseRefName --jq .baseRefName 2>/dev/null) if [ -z "$base_branch" ]; then base_branch=main echo "no linked PR found (or the query failed); falling back to repository default branch 'main'" fi$base_branch— never a hardcodedorigin/main— in every step below, including "Merge conflict resolution." - Check whether the branch is actually behind its base before rebasing — rebasing when it isn't is pure churn (it replays every commit and changes only their SHAs, giving you nothing to push):
Ifgit fetch origin "$base_branch" behind_count=$(git rev-list --count HEAD..origin/"$base_branch")$behind_countis0, skip the rebase — the branch is already up to date. Otherwise:git rebase "origin/$base_branch" - Resolve any merge conflicts the rebase produced (the base may have moved since Review) — see "Merge conflict resolution — CRITICAL" immediately below. If the rebase completed with no conflicts, skip straight to step 5.
- Once the rebase is clean — no conflicts, or all resolved per step 4 — push it immediately if a rebase ran:
A rebase rewrites every replayed commit's SHA, so the result will never matchgit push --force-with-leaseorigin/<branch>byte-for-byte — that mismatch is expected, not a fault.--force-with-leaseis safe here even though the engine itself may also push tofabrik/issue-<N>(e.g. its own worktree-push helper, or a WIP commit pushed between your fetch and your push): a lease rejection from that just means the remote moved — the correct response is to retry (see below), never to force past 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.
- 9d ago First seen · 475 lines · 36 tokens per session scan A d8586fd28d51
fabrik-validate is a skill published in the GitHub repository handarbeit/fabrik (22 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 8,657 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-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
agent-qa-testing
Agent davranis testi ve protokol uyumluluk dogrulamasi. Agent'larin tanimli rollerine uygun davranip davranmadigini assertion-based test'lerle olcer. Personality drift, role violation ve output kalite regresyonu tespit eder.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.
vitest
Set up Vitest testing in any project — detects type (Cloudflare Workers, React, Node, library), generates vitest.config.ts, test setup, utilities, and a sample test. Covers mocking patterns, coverage config, workspace setup, Jest migration. Use whenever the user mentions adding tests, setting up Vitest, configuring…
pre-ship-review
Run a structured quality review before shipping code at any checkpoint such as PRs, releases, or milestones. Use whenever the user says.