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 anatolykoptev/dozor --skill security-auditgit clone --depth 1 https://github.com/anatolykoptev/dozorWrote 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/anatolykoptev/dozor/security-audit)<a href="https://agentmods.dev/skills/anatolykoptev/dozor/security-audit"><img src="https://agentmods.dev/badge/skills/anatolykoptev/dozor/security-audit/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/anatolykoptev/dozor/security-audit"><img src="https://agentmods.dev/badge/skills/anatolykoptev/dozor/security-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00036 | $0.00574 |
| Opus 5 | $0.00018 | $0.00287 |
| Sonnet 5 | $0.00007 | $0.00115 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
security-audit 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 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.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Audit
Systematic security review using Dozor inspection tools.
Audit Flow
1. NETWORK — exposed ports, container isolation
server_inspect(mode: "security")
2. SERVICES — running versions, known vulnerabilities
server_inspect(mode: "health")
3. SSL — certificate expiry and configuration
server_inspect(mode: "remote") <- checks remote server SSL
4. ACCESS — authentication, API keys, exposed endpoints
server_inspect(mode: "security")
5. RESOURCES — unusual disk/memory/CPU patterns
server_inspect(mode: "overview")
What to Check
Network Exposure
- Ports bound to 0.0.0.0 vs 127.0.0.1
- Services that should be internal-only (postgres, redis, rabbitmq)
- Docker network isolation between containers
- Firewall rules (ufw/iptables)
Container Security
- Containers running as root
- Privileged containers
- Unbounded resource limits (memory, CPU)
- Outdated base images
SSL/TLS
- Certificate expiry < 14 days = WARNING, < 7 days = CRITICAL
- HTTP to HTTPS redirect working
- TLS version (should be 1.2+)
Authentication
- API endpoints without auth
- Default passwords on services
- Exposed management ports (RabbitMQ management, Qdrant dashboard)
Logs
- Failed SSH login attempts
- Repeated 401/403 in nginx
- Unusual access patterns (high request rate from single IP)
Severity Classification
| Finding | Severity |
|---|---|
| Service bound to 0.0.0.0 with no auth | P0 |
| SSL expires < 7 days | P0 |
| Container running as root with volumes | P1 |
| SSL expires < 14 days | P1 |
| Outdated base images | P2 |
| Missing rate limiting | P2 |
Audit Report Format
## Security Audit — [date]
### Status: [PASS / NEEDS ATTENTION / CRITICAL]
### Findings
1. [severity] [description] — [recommendation]
2. ...
### Positive
- [good practices in place]
### Recommendations
- [prioritized action items]
Rules
- Security audit is read-only — never change configs during audit
- Report findings, recommend fixes, let user decide
- Escalate P0 security findings to orchestrator immediately
- Run security audit as part of full reports (reporting skill)
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 · 93 lines · 36 tokens per session scan A dc8c0c175fee
security-audit is a skill published in the GitHub repository anatolykoptev/dozor (5 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 574 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 2026-08-31.
Other skills, from other repositories
github_read
Read access: repos, issues, PRs, files, branches, workflows, runs.
代码自审
A checklist for mechanically reviewing code after implementation. It checks module boundaries, dependency cycles, requirement links, lint and type errors, security issues, and repeated or dead code.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
frontend-feature
Build a new page, view, or data-driven feature in the Next.js frontend. Use when adding a route under the dashboard/marketing area, wiring UI to a backend endpoint, adding client state, or creating a localized page. Covers App Router, data fetching, Zustand stores, and i18n.
prs-awaiting-maintainer
List open pull requests where the ball is in the maintainer's court: CI is green and the PR is ready for a maintainer to review, re-review, or merge. Use when the user wants to see PRs awaiting maintainer action.