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 gebruder/wirken --skill aggregatorgit clone --depth 1 https://github.com/gebruder/wirkenWrote 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/gebruder/wirken/aggregator)<a href="https://agentmods.dev/skills/gebruder/wirken/aggregator"><img src="https://agentmods.dev/badge/skills/gebruder/wirken/aggregator.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Rogue Agent · line 60 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00030 | $0.01105 |
| Opus 5 | $0.00015 | $0.00553 |
| Sonnet 5 | $0.00006 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
aggregator 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 8d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Aggregator
Fires once per day on a cron the operator configures. Performs a strict-pipeline run over the source allowlist:
- Fetch each source in
sources.tomlvia the declared method (RSS / API / rate-limited scrape). The HTTP wrapper enforces the egress allowlist. - Normalize fetched items into candidate records:
title,source,date,url,body_excerpt,citation_json. - Skip if the candidate's content hash is already in the seen set.
- Score the candidate's relevance against the user's interests file (
~/.wirken/zirkel/interests.toml). Output: a float in[0, 1]plus a one-linewhy_surfacedrationale that names the matched interest. - If the score crosses the keep threshold and no skip pattern matches, write the candidate to the local SQLite store. Otherwise, log the skip with reason.
- After all sources fetched, cluster the run's kept candidates into emergent themes using a small local embedding model.
- Render the digest as plain prose with footnote-ready citations on every item. Push to the configured channel adapter.
Aggregator does not synthesize claims about the world. The digest reads as "N items kept, M skipped. Today's themes: [theme A: items 1, 4; theme B: items 2, 3, 7]. Each item links to its source with a one-line why-surfaced explanation." No "today the regulators are saying X" prose.
This skill is disable-model-invocation: true. Reach it via /aggregator (manual run) or via the operator's cron that calls the underlying CLI command directly.
State
~/.wirken/zirkel/zirkel.db— SQLite database holding candidates, seen, themes, skipped_log, runs, and the cached interests snapshot per run.~/.wirken/zirkel/interests.toml— user-editable; reloaded at the start of every run; a hash of the file is recorded in the audit log so changes are visible run-to-run.~/.wirken/zirkel/bodies/— full bodies referenced bycandidates.body_full_pathfor items where the excerpt is too small for retrieval.
The aggregator and librarian share this state; both skills are scoped to the same ~/.wirken/zirkel/ directory by their permissions blocks.
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.
- 8d ago First seen · 81 lines · 30 tokens per session scan A bc47bdd4eb55
aggregator is a skill published in the GitHub repository gebruder/wirken (171 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 1,105 once invoked, about $0.0002 per session on Opus 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
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
aig-scanner
A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard. Uses built-in exec + Python script, no plugin required. Requires AIGBASEURL to be configured. Triggers on: scan AI service, AI vulnerability scan, scan AI infra…
cocotrace
Build and query the SHA-256 requirements-to-implementation traceability graph across lifecycle artifacts.
cocoaudit
View and export the append-only session audit trail for regulated environments.
defenseclaw-ops
Manage DefenseClaw enterprise security - scan components, manage tool permissions, view alerts, configure guardrails.
squirrelscan
Skill "squirrelscan" from squirrelscan/squirrelscan, covering squirrelscan cli, links, install, command overview and quickstart.