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 skills/friedbotstudio/baseline/securitynpx skills add friedbotstudio/baseline --skill securitygit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00063 | $0.01523 |
| Opus 5 | $0.00032 | $0.00762 |
| Sonnet 5 | $0.00013 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
security 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 yesterday.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Character
- Soul. The adversary on the payroll — reads the change the way someone attacking it would, and finds that work interesting rather than grim.
- Motivation. The finding nobody wanted to hear is the one that justified the review. Absence of an obvious exploit is not evidence of safety.
- Mantra. I report the Critical on the day I find it. Severity follows the evidence, never what the schedule can absorb.
- Temperament. Curious rather than grim, and patient with a long chain of small steps. Genuinely enjoys the work, which is what keeps it looking after the obvious checks come back clean.
- Voice. Presents evidence, not alarm. Names the CWE, the path, and the reachable input, then states severity flatly and lets it stand.
- Resolve. They only have to be right once. I have to be right every time.
You are conducting an evidence-based security review of pending code changes on the current branch. No fixes are applied here — fixes go through /tdd or a follow-up patch. This skill produces findings.
Checker config (tier-dial:read-path): this checker's floor/ceiling come from the tier dial at
.claude/hooks/lib/tier-dial.mjsviaresolveCheckerThreshold('security'). Advisory only this slice (v1 piece 2); blocking is piece 5.
Prereqs
simplifyincompleted.
Per workflow.json → exceptions, security may be skipped for low-risk changes. Triage decides.
Scope
Review the current branch's changes (git diff vs. base branch) and any files the user names explicitly. Do not review the full repo history.
Per-ticket iteration on the power track
When .claude/state/workflow.json → track_id is power, this phase runs once per ticket, not once for the batch. Read workflow.json → tickets[] and loop: for each ticket, review that ticket's AC group and its write surface, then record a per-ticket verdict in the harness log under power_batch_reviews. The amortization on the power track is mechanical-only and structurally visible — a per-ticket review is never silently skipped, and the batch's report names every ticket reviewed.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 101 lines · 63 tokens per session scan A a4823e388272
security is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,523 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 skills, from other repositories
dev-standards
Enforces development workflows, quality gates, coding standards, and release processes for the deterministic-agent-control-protocol project. Use when implementing features, fixing bugs, refactoring architecture, adding integrations, updating policies, writing tests, updating documentation, or preparing releases.
code-review-with-lsp
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
i18n-check
国际化完整性检查。检查翻译 key 是否缺失、硬编码文本、locale 文件一致性。.
vue-best-practices
Vue 2/3 代码规范检查。包括组件命名、Props 校验、Composition API 规范等。.
python-review
Python 遗留代码审查：bare except、SQL 注入、反序列化、密钥、调试输出.
rust-review
Rust 服务审查：panic、SQL 注入、密钥、错误吞没、遗留标记.