briefbound-competition-research-lifecycle

briefbound-competition-research-lifecycle is a skill for Claude Code, Codex from CCDawn/codex-skills. It costs 49 tokens per session (995 once invoked), scanned A, original, MIT.

A coordination procedure for research competitions and benchmark programs. A benchmark is a repeatable test used to compare systems; this procedure tracks rules, data, baselines, experiments, evidence, and submissions across the program.

In plain words
What is it for?
Use it to coordinate benchmark rules, datasets, baseline systems, experiments, claims, submission checklists, and external feedback while routing each concrete task to the right specialist.
Why use it?
It keeps facts and dependencies aligned between stages so that changing rules, data, metrics, or evidence does not invalidate later results.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the briefbound-skills plugin — 30 skills shipped together

Good fit Use it to coordinate benchmark rules, datasets, baseline systems, experiments, claims, submission checklists, and external feedback while routing each concrete task to the right specialist.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ccdawn/codex-skills/briefbound-competition-research-lifecycle
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.

Any agent
npx skills add CCDawn/codex-skills --skill briefbound-competition-research-lifecycle
Clone the repo
git clone --depth 1 https://github.com/CCDawn/codex-skills

Made for: Claude Code, Codex.

Or install briefbound-skills, the plugin that ships this one along with the rest of its 30 skills.

Wrote 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.

agentmods badge for briefbound-competition-research-lifecycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-competition-research-lifecycle/github.svg)](https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-competition-research-lifecycle)
Your own site
<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-competition-research-lifecycle"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-competition-research-lifecycle/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.

agentmods 80×15 button for briefbound-competition-research-lifecycle

Your own site · 80×15
<a href="https://agentmods.dev/skills/ccdawn/codex-skills/briefbound-competition-research-lifecycle"><img src="https://agentmods.dev/badge/skills/ccdawn/codex-skills/briefbound-competition-research-lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00049 $0.00995
Opus 5 $0.00024 $0.00498
Sonnet 5 $0.00010 $0.00199
Haiku 4.5 $0.00005 $0.00100

Measured 9d ago against content hash 18f1c913d644, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

briefbound-competition-research-lifecycle 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.

skills/research/briefbound-competition-research-lifecycle/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Briefbound 竞赛科研全流程

目标

维护竞赛/benchmark 项目的阶段边界、事实源和跨阶段依赖,让当前最具体 owner 连续推进。它是全项目协调层,不重复执行研究、score、写作或工程流程。

Briefbound task contract

  • Context Boundary: 竞赛规则、数据/metric、active baseline/evidence、当前阶段、关键 artifact、提交约束和截止时间。
  • Output Contract: 当前阶段判断、跨阶段风险、一个 primary owner、阶段完成证据和下一阶段动作。
  • Allowed Action: 读取项目事实源并协调当前阶段;具体实验、工程、审查和写作由最具体 owner 执行。
  • Success Evidence: 规则/数据版本、baseline/实验记录、claim 来源、submission checklist 或外部反馈中的阶段必要证据。
  • Stop Condition: 规则/metric/数据漂移、active evidence 冲突、关键提交要求未知、claim 无来源或继续会污染有效证据。
  • Route Out: 当前阶段 owner、briefbound-ai-research-loopbriefbound-score-loopbriefbound-research-rigor-review、工程 owner、briefbound-router 或 BLOCKED。

统一调用契约

  • 只处理 Briefbound task contract 范围;不匹配时回 briefbound-router 或更具体 owner,复合任务不吞其他 owner。
  • 用户可见内容默认中文,完成只报状态、产出、证据和剩余风险;代码、命令、路径、错误原文、API/协议、skill 名和枚举保留原样;Route Out 仅以 Briefbound task contract 为准,末行写 下一步建议: <一个具体动作>

激活闸门

只有请求跨越至少两个阶段,或规则、数据、baseline、claim、submission 之间的依赖需要统一治理时进入。单次论文复现/消融用 AI Research,反复 metric 晋升用 Score Loop,关键 claim 审查用 Rigor Review,具体工程故障用对应工程 owner。

阶段地图

按项目实际情况映射,不强制创建八套 artifact:规则与目标 -> 数据/协议 -> baseline -> 研究实验 -> 证据综合/claim -> 提交或发布

每次只维护:当前阶段、active truth、阻塞下一阶段的最小缺口、primary owner、完成证据。已有项目工件优先;缺少模板但不影响当前决策时继续,不为形式补文档。

协调规则

  1. 先读取最相关的规则、metric、数据版本、baseline、实验结果、claim map 或提交清单,不扫描所有阶段。
  2. 识别当前阶段及最早失效的上游证据;上游漂移时标记受影响下游为 stale 并回退修复。
  3. 选择一个能直接产生下一阶段必要证据的 primary owner。当前 owner 完成后,若下一阶段明确且已授权,连续路由,不逐阶段询问。
  4. AI Research 可以内部完成简单实验;只有反复晋升/榜单 lane 才下沉 Score Loop。普通 candidate gate 不经过 Rigor Review。
  5. 只有论文/对外 claim、方向转向、重要 best-known 结果或高成本投入才进入 Rigor Review。
  6. 并行只用于真正独立的 artifact 和写入面;不默认创建 3-6 lanes、worktree 或多 Agent。

Smoke/proxy 只用于可运行性、淘汰和排序,不替代正式目标评估。外部 leaderboard 是重要校准证据,但不能静默改变本地 protocol 或 claim 范围。

输出

阶段: <当前阶段>
- Active truth: <规则/数据/baseline/evidence>
- 关键缺口或漂移: <仅真实项>
- Primary owner 与产出:
- 阶段完成证据:
下一步建议: <一个具体动作>

跨会话或正式交接时才读取 references/lifecycle-reference.mdreferences/templates.md;需要校准典型阶段切换时读取 references/examples.md。普通推进不输出完整 lifecycle 表、Briefbound gate 或阶段菜单。

Read the full file on GitHub · 60 lines

Files

What ships with it

4 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. 9d ago First seen · 60 lines · 49 tokens per session scan A 18f1c913d644

Subscribe to this mod's changes

briefbound-competition-research-lifecycle is a skill published in the GitHub repository CCDawn/codex-skills (4 stars, last pushed 27d ago), licensed MIT. It adds 49 tokens to every session and 995 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.