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/chorenpx skills add friedbotstudio/baseline --skill choregit 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 | $0.00183 | $0.03404 |
| Opus 5 | $0.00092 | $0.01702 |
| Sonnet 5 | $0.00037 | $0.00681 |
| Haiku 4.5 | $0.00018 | $0.00340 |
Grade A, and why
chore 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 2d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
chore — workflow for tasks that don't need TDD
This skill runs a stripped-down workflow for tasks where nothing is meaningfully driven by a failing test. The full /tdd RALPH cycle is theatre when the change is "fix a typo", "update a count", "remap a vendored path", or "tighten a description" — there is no test that catches a typo, and the project audit (or a downstream lint) serves as the regression check.
The chore workflow exists so this class of work can move with the right ceremony — real verification of "did I break anything" without the scenario+implement loop, and conditional simplify/integrate/document passes when the diff actually warrants them.
Definition: when is a task a chore?
A task is a chore if and only if it has no code changes that need TDD. Concretely, a chore is anything from this list:
- Documentation edits —
README.md,CLAUDE.mdprose,docs/init/seed.mdprose, governance count refreshes, skill SKILL.md descriptions, reference docs. - Vendored-skill content updates — path remaps (e.g.
.agents/→.claude/skills/), count refreshes, "Related Skills" annotations, license-required modification notices. - Configuration tweaks —
project.json,.mcp.json,settings.jsonedits whose behavioural effect is config-driven (a new declaration, a flipped flag) rather than code-driven. - Formatting / typo fixes anywhere in the repo.
- Dependency bumps where no project code changes alongside.
- Skill consolidation moves — collapsing a single-consumer skill into its consumer's
references/directory. - File renames or path remaps with no behavioural change.
A task is not a chore if any of:
- New runtime behaviour is being added — the failing test is the only way to drive it correctly.
- A bug is being fixed and regressing to that bug would be undetectable without a test — the fix SHALL come with a test.
- A refactor changes behaviour under specific inputs — TDD captures the boundary.
The classification rule is: if there is no failing test that should exist for this work, it is a chore. Otherwise it is /tdd (or higher).
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.
- 2d ago First seen · 129 lines · 183 tokens per session scan A fd1b7d1d634d
chore is a skill published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 183 tokens to every session and 3,404 once invoked, about $0.0009 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.