onescience-coder

A step-by-step coding workflow for OneScience projects. It gathers project knowledge, breaks work into confirmed steps, implements each step, and runs checks when finished.

In plain words
What is it for?
Use it for staged implementation tasks that need resource lookup, user confirmation before edits, reuse of existing code, and up to six basic training or model-path smoke tests.
Why use it?
It reduces guesses about missing requirements and keeps coding, handoffs, and final verification organised.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/onescience-ai/oneskills/onescience-coder
Any agent
npx skills add onescience-ai/OneSkills --skill onescience-coder
Clone the repo
git clone --depth 1 https://github.com/onescience-ai/OneSkills

Made for: Claude Code, Codex.

Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,781 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00101 $0.01781
Opus 5 $0.00051 $0.00890
Sonnet 5 $0.00020 $0.00356
Haiku 4.5 $0.00010 $0.00178

Measured 2d ago against content hash 8ab252d35fcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onescience-coder 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.

skills/onescience-coder/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

输入获取方式

本技能支持两种输入方式:

  1. 上下文 handoff(默认):从调用方传入的 step_handoff 获取任务信息。
  2. 文件 handoff(autonomous_mode):从 .onescience/handoff/step_{step_id}.yaml 读取任务信息。执行后,将结果写入 .onescience/handoff/step_{step_id}_result.yaml

启动时优先检查 .onescience/handoff/ 目录是否存在对应的交接文件;若存在则使用文件模式,否则使用上下文模式。

文件交接格式参见 skills/onescience-orchestrator/references/file_handoff_contract.md

OneScience Coder

你是 OneScience 的代码实现执行技能(type=executor)。你的职责是:基于资源技能返回的内容完成分步编码,并在所有步骤完成后给出最终验证结果。

核心职责

  1. 接收任务后立即调用 type=resource 技能获取规格知识、使用知识和规划决策知识。
  2. 基于资源内容规划目录结构、识别步骤依赖,并把任务拆成可独立确认和执行的步骤。
  3. 每个步骤都先输出详细执行信息,等待用户确认后再编码。
  4. 编码时优先复用已有实现,保持最小改动,不猜测缺失契约。
  5. 所有步骤完成后,若本地环境支持最小冒烟测试则优先执行全路径冒烟测试(forward/backward/train_loop/val_loop/CL/config 共 6 项,最多 6 次),否则执行静态需求一致性检查。
  6. coder 只拥有当前编码步骤,不决定后续业务 executor;运行、环境、后续训练/推理/评估等下一阶段由调用方或 onescience-orchestrator 决策。
  7. 若上游 step_handoff.tier_config 存在且当前步骤对应 tier_0_smoke,冒烟测试的 6 项检查结果需写入 execution_result.tier_result 回传给 orchestrator。

硬约束

  • 接收任务后必须立即调用 type=resource 技能获取资源;无论调用者是否提供了 reference_resources,都不能跳过。
  • resource_retrieval_request 是技能间控制消息,不是面向用户的执行结果;不得只输出请求 YAML 后停止。构造请求后必须调用或内联执行匹配的 type=resource 技能,取得 resource_retrieval_result 后再继续资源筛选与步骤规划。
  • 每个步骤如需补充知识,必须再次调用 type=resource 技能;不能沿资源 path 直接读取文件补洞。
  • 允许作为编码依据的只有两类内容:
    • reference_resources[*].content
    • resource_retrieval_result.matched_resources[*].content
  • reference_resources[*].pathresource_bindings[*].pathmatched_resources[*].path 只用于标识和追踪,不授权直接读文件。
  • coder 可以读取自身 references/*.md 工作流文档;这些文档属于本技能协议,不属于资源技能返回内容。
  • 没有运行证据时,不得声称“已验证通过”。
  • 冒烟测试仅在当前环境已经具备最小运行条件时才能执行;不得为了冒烟测试安装 conda 环境、创建新环境或安装额外依赖包。

必须读取的参考文档

  • 进入分步执行前,必须读取:references/stepwise_coding_workflow.md
  • 开始编码前,必须读取:references/coding_conventions.md
  • 当最终验证进入静态检查分支时,必须读取:references/static_requirement_review.md

顶层流程

接收任务
-> 强制调用 type=resource 技能获取资源
-> 初始资源筛选
-> 规划目录结构与步骤依赖
-> [循环] 对每个步骤:
   - 必要时补充资源
   - 输出详细执行信息
   - 等待用户确认
   - 执行当前已确认步骤
-> 所有步骤完成后:
   - 若本地环境支持最小冒烟测试 -> 进行冒烟测试(最多 6 次)
   - 否则 -> 执行静态需求一致性检查
-> 返回 execution_result

Read the full file on GitHub · 141 lines

Files

What ships with it

3 files 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.

Changes

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.

  1. 2d ago First seen · 141 lines · 101 tokens per session scan A 8ab252d35fcd

Subscribe to this mod's changes

onescience-coder is a skill published in the GitHub repository onescience-ai/OneSkills (18 stars, last pushed 19d ago), licensed MIT. It adds 101 tokens to every session and 1,781 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.

Related

Other skills, from other repositories

apm-usage

Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any apm CLI command.

microsoft/apm · 49 tokens

clean-user-facing-text

Audit and finalize authorized natural-language text meant for readers: strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI…

ShadowAqueduct/watermark-remover · 121 tokens

sessions

Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened recently, or any question about past agent sessions. Also use when the user references prior…

slopus/happy · 78 tokens

map-review

Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.

azalio/map-framework · 58 tokens

runjam-defaults

Default constraints for every RunJam session. Defines output path conventions, dependency checking rules, fallback strategies, and file management discipline. This skill is auto-injected into every session — do not remove. Current session working directory: /Users/guizhan/work/code/runjam.

peintune/runjam · 59 tokens

map-fast

Minimal workflow for small, low-risk changes — no planning, no learning.

azalio/map-framework · 17 tokens