project-continuity

A guide for keeping a long-running software project aligned across multiple work sessions. It separates lasting goals and repository rules from temporary state, history, and handoff notes.

In plain words
What is it for?
It is for setting up, checking, repairing, resuming, or handing off project continuity across repositories, sessions, and development tasks.
Why use it?
It reduces confusion caused by stale instructions, conflicting checkpoints, forgotten decisions, or work resumed in the wrong repository or version.

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/macintog/codex-spine/project-continuity
Any agent
npx skills add macintog/codex-spine --skill project-continuity
Clone the repo
git clone --depth 1 https://github.com/macintog/codex-spine

Made for: Claude Code, Codex.

Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,883 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 $0.00084 $0.02883
Opus 5 $0.00042 $0.01442
Sonnet 5 $0.00017 $0.00577
Haiku 4.5 $0.00008 $0.00288

Measured 2d ago against content hash 885bee059215, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-continuity 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit-continuity.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/project-continuity/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Continuity

Keep a long-lived project aligned on purpose while narrow implementation work changes. The goal is a compact, discoverable continuity contract, not more documentation.

Concrete bootstrap tools, memory retrieval, Git mechanics, indexing, and local proof commands belong to the installed environment or a tooling guide the repository explicitly claims. Do not infer a repo-local codex/TOOLING.md or a Git policy from this skill.

Workflow

  1. Bind the latest explicit user-selected task subject before reading a packet as actionable: objective and scope, canonical repository or system, exact worktree/ref/HEAD or runtime identity, and current authority/evidence. A goal, queue, checkpoint, prompt, packet, index hit, or worker output is evidence only until every binding field matches.
  2. Infer the mode: inspect is read-only; adopt establishes a packet; repair separates mixed roles; resume reconciles the handoff with the bound subject and current evidence; handoff refreshes current state and archives displaced detail.
  3. Establish the authority scope: one repository, a multi-repository workspace, or one product or program spanning repositories. Start unfamiliar ownership at undetermined; then establish repo-native-only, local-overlay, or repo-local from evidence. Treat in-tree-adoption and repo-native only only as deprecated read aliases; never write them back.
  4. Inspect the applicable AGENTS.md and AGENTS.override.md instruction chain for the current working directory, native documentation and source-of-truth files, existing continuity and ownership declarations, repository and publication posture, and conflicting, duplicated, stale, generated, or sensitive material. Stay read-only until the current task and repository policy authorize writes.
  5. Reconcile each fact into exactly one role: durable product authority, repo-local working rule, advisory volatile handoff state, durable decision or deep reference, or historical evidence. Treat every checkpoint and state anchor as a claim about prior state, not proof or task selection.
  6. Apply the smallest idempotent change. Preserve truthful native guidance, merge rather than replace existing agent rules, avoid duplicating current state, and make no changes when the existing packet is healthy.
  7. Verify that a fresh agent can discover the packet without knowing this skill exists, pointers resolve, current-state claims match repository or runtime evidence, template instructions and secrets are absent, and only the intended startup files load routinely. Run scripts/audit-continuity.py --root <path> --json when this skill's bundled auditor is available. A stale or fail result blocks resume and handoff; it is never authority to write or to follow another file's next step.
  8. Return the mode, scope, posture, inspected and changed files, authority conflicts resolved, verification performed, and unresolved decisions or missing authority. End terminally: residuals are non-directive findings, not a generated successor task.

Read the full file on GitHub · 153 lines

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 · 153 lines · 84 tokens per session scan A 885bee059215

Subscribe to this mod's changes

project-continuity is a skill published in the GitHub repository macintog/codex-spine (9 stars, last pushed 2d ago), licensed MIT. It adds 84 tokens to every session and 2,883 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

bensz-rmd-rules

规范 AI 开发 R Markdown 分析脚本的行为准则。当用户要求"写 Rmd 分析"、"开发 R 脚本"、"做数据分析"时触发。核心原则:遵循主业与副业分离架构(.R 保留完整数据,.Rmd 应用业务阈值),优先使用用户已有 R 包资源;图表默认按 Nature 级别可读性与出版质量生成;专家级解读兼顾弱背景读者,提供四层框架、指标导读与不常用指标首次解释协议;路径验证确保跨平台兼容性。前提:luckyBase 为硬依赖。.

huangwb8/skills · 157 tokens

auto-test-project

当用户明确要求"测试项目"、"运行 auto-test-project"或"进行项目级测试"时使用。对完整项目进行多轮 A 轮批判性测试 + B 轮质量检查,系统化发现、记录、修复问题。⚠️ 不适用:用户只是想优化功能(应直接修改)、只是询问项目问题(应直接回答)、没有明确"测试"意图。.

huangwb8/skills · 94 tokens

auto-test-code

当用户明确要求"测试代码"、"运行代码审查"或"进行代码自检"时使用。通过多轮 A 轮批判性代码审查 + B 轮代码质量原则检查,系统化发现、记录、修复程序代码中的问题,并将计划/过程/结果统一沉淀到目标代码根目录的 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-code/{yyyy-mm-dd-hh-mm}/output/tests/ 隔离工作区。⚠️ 不适用:用户只是想优化功能(应直接修改)、只是询问代码问题(应直接回答)、没有明确"测试代码"意图。.

huangwb8/skills · 154 tokens

auto-test-skill

当用户明确要求"测试技能"、"运行 auto-test"或"进行批判性测试"时使用。通过多轮 A 轮批判性测试 + B 轮质量原则检查,系统化发现、记录、修复问题,并沉淀可追溯的 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-skill/output/plans/ 与 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-skill/output/tests/ 文档。⚠️ 不适用:用户只是想优化功能(应直接修改)、只是询问技能问题(应直接回答)、没有明确"测试"意图。.

huangwb8/skills · 158 tokens

frontend-specialist

前端开发专家。用于前端应用、页面、组件、现有 UI 增量改进、已有页面视觉优化、UI/UX 改造、视觉重设计、响应式布局、表单和输入框视觉一致性、设计系统落地、React/Vue/Next.js/Nuxt、Tailwind、shadcn/ui、Radix、MUI、AntD、仪表盘、SaaS、Landing Page、移动端适配、前端性能优化、浏览器截图检查和去除 AI 味 UI。触发后应把“做好看”转化为可执行设计约束,优先复用项目现有组件与视觉语言,小步实现并尽量通过浏览器或 Playwright 做视觉反馈闭环;当用户要改进当前页面或已有界面时,默认先诊断再做局部优化,而不是从 0 重做。.

huangwb8/skills · 198 tokens

git-pr-review

当用户明确要求“review 某个 GitHub PR”“评估某个 pull request 是否值得 merge”“帮我判断这个 PR 怎么处理”时使用。基于用户提供的 GitHub 仓库地址、PR 编号/链接和补充说明,进行只读、证据驱动的 PR 审查:理解 PR 解决的问题、评估方案优劣与局限、默认优先使用内置“好 PR”标准并在必要时联网补充、识别恶意或高风险改动,并输出是否建议 merge 的 Markdown 决策报告。⚠️ 不适用:用户要你直接修改 PR 代码、直接 merge PR、或在本地执行 PR 分支中的不可信代码。.

huangwb8/skills · 163 tokens