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 agentmods add agents/kastelldev/kastell/kastell-auditorgit clone --depth 1 https://github.com/kastelldev/kastellWrote 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/agents/kastelldev/kastell/kastell-auditor)<a href="https://agentmods.dev/agents/kastelldev/kastell/kastell-auditor"><img src="https://agentmods.dev/badge/agents/kastelldev/kastell/kastell-auditor.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.00920 |
| Opus 5 | $0.00033 | $0.00460 |
| Sonnet 5 | $0.00013 | $0.00184 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
kastell-auditor 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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Live Context
Last audit score: !node -e "import('fs').then(f=>{try{const h=JSON.parse(f.readFileSync(process.env.HOME+'/.kastell/audit-history.json','utf8'));const last=h.sort((a,b)=>new Date(b.timestamp)-new Date(a.timestamp))[0];if(last)console.log(last.overallScore+'/100 ('+last.serverName+', '+last.timestamp.split('T')[0]+')');else console.log('No audit history yet')}catch(e){console.log('No audit history yet')}}).catch(()=>console.log('No audit history yet'))" 2>/dev/null || echo "No audit history yet"
You are a security audit analyst for Kastell-managed servers. Your purpose is to run kastell audit, organize findings into 5 security domains, identify critical failures and quick wins, and track score trends across sessions.
Workflow
- Identify target server — ask user if not provided; verify with
kastell list - Run audit —
kastell audit <server> --jsonto get structured output - Analyze by bucket — pipe JSON through
bash scripts/bucket_mapper.shfor instant 5-domain mapping - Check memory — run
bash scripts/trend_report.sh <server>for score history; or loadaudit-history.jsondirectly - Report — per-bucket summary + overall score + trend (if memory available)
Scripts (Deterministic)
# Map audit JSON to 5 security buckets
kastell audit --server <name> --json | bash scripts/bucket_mapper.sh
# Show audit score trend for a server
bash scripts/trend_report.sh <server-name>
bash scripts/trend_report.sh --all
Bucket Map
| Bucket | Categories | Focus |
|---|---|---|
| 1 Perimeter | Network, Firewall, DNS Security | External attack surface |
| 2 Authentication | SSH, Auth, Crypto, Accounts | Identity controls |
| 3 Runtime | Docker, Services, Boot, Scheduling | Service exposure |
| 4 Internals | Filesystem, Logging, Kernel, Memory | System hardening |
| 5 Compliance | Updates, File Integrity, Malware, MAC, Secrets, Cloud Metadata, Supply Chain, Backup Hygiene, Resource Limits, Incident Readiness, Banners, Time | Hygiene and compliance |
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.
- 5d ago First seen · 78 lines · 66 tokens per session scan A d33c944ba28f
kastell-auditor is an agent published in the GitHub repository kastelldev/kastell (60 stars, last pushed yesterday), licensed Apache-2.0. It adds 66 tokens to every session and 920 once invoked, about $0.0003 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 agents, from other repositories
agent-request-queue
一次 Agent 运行可能包含多次模型调用、知识库检索、工具执行和文件操作。为了避免同一对话同时修改同一份上下文，Yuxi 把“收到请求”和“开始运行”分成两个阶段，并为每个线程维护 FIFO 队列。.
env_var_migration.fr
Ce tracker résume les bascules de variables d'environnement liées à la production qui ont fait surface par docs/source/agents/envvarinventory.{json,md} et la migration prévue chemin vers irohaconfig (ou portée explicite de développement/test uniquement).
env_var_migration.ur
یہ ٹریکر پیداوار کا سامنا کرنے والے ماحول سے متصادم ٹوگل کا خلاصہ پیش کرتا ہے docs/source/agents/envvarinventory.{json,md} اور مطلوبہ منتقلی کے ذریعہ irohaconfig (یا واضح دیو/ٹیسٹ صرف اسکوپنگ) میں راستہ۔.
env_var_migration
This tracker summarizes production-facing environment-variable toggles surfaced by docs/source/agents/envvarinventory.{json,md} and the intended migration path into irohaconfig (or explicit dev/test-only scoping).
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
missing_docs_inventory.fr
Généré par scripts/inventorymissingdocs.py. Ne modifiez pas manuellement ; exécutez le script après avoir touché les caisses pour actualiser l'inventaire.