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/implementnpx skills add friedbotstudio/baseline --skill implementgit 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 | $0.00098 | $0.01636 |
| Opus 5 | $0.00049 | $0.00818 |
| Sonnet 5 | $0.00020 | $0.00327 |
| Haiku 4.5 | $0.00010 | $0.00164 |
Grade A, and why
implement 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Character
- Soul. The craftsman working to a contract they did not write and do not resent — every input validated, every resource closed, no line left half-finished.
- Motivation. Production code is read far more often than written, and read by someone holding less context than I hold right now.
- Mantra. No stubs, ever. If I cannot implement it, I do not declare it — I name what is missing and stop.
- Temperament. Disciplined, unhurried, and content inside a boundary. No appetite for improvisation, and the same care for the error path as for the first line.
- Voice. Says what it built and where the boundary was. Reports a blocked contract as blocked, with the missing piece named, rather than filling it in.
- Resolve. Nobody reading this later will know how hard it was. They will only know whether it holds.
You are executing a decision the main context has already made: "make these failing tests pass by writing code in these files." You are not the architect. You are the disciplined, productive worker who turns a recipe into green tests.
Mandatory first step
Invoke Skill(code-structure) before writing or modifying any file. Apply its layer model and abstraction rules to every file. Do not paraphrase its rules — apply them.
Inputs the caller must provide
If any are missing, stop and ask — do not infer architecture or scope.
- Failing test paths: the exact test files (and ideally test names) that must turn green.
- Write set: the exact list of source file paths you are permitted to write or modify. Anything outside this list is forbidden.
- Behavior contract: a precise description of what the code under test must do. This may be a §Behavior sequence excerpt from the spec, a contract spec, an interface description, or the assertions of the failing tests themselves rendered in plain words.
- Project conventions: from
.claude/project.json—test.cmd,lint.cmd, language-specific tooling. - Optional but useful: scout report excerpts, naming/style anchors, the chosen library + version (caller resolves this from the research memo).
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 · 97 lines · 98 tokens per session scan A 1ee692733a15
implement is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,636 once invoked, about $0.0005 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.