agentmods.dev

cadence-resume

cadence-resume is a skill for Claude Code from hxt9805/cadence. It costs 65 tokens per session (2,961 once invoked), scanned A, original, MIT.

A session-resume helper for the cadence project workflow, which stores conversation handoffs so work can continue after starting a new session.

In plain words
What is it for?
Use it to resume a previous discussion, review where it stopped, see changes in the project records, or start a new session.
Why use it?
It avoids searching through old conversations or losing track of previous decisions. It shows saved handoffs, loads the selected context, and compares it with the current project records.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cadence plugin — 5 skills, 3 commands, 3 agents, 1 hook shipped together

not rated 5repo 1mo ago A scan 65 tokens original MIT

Good fit Use it to resume a previous discussion, review where it stopped, see changes in the project records, or start a new session.

Compare 6 skills from other repositories ↓
View source ↗ hxt9805/cadence
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add hxt9805/cadence
Claude Code
/plugin install cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 5 skills, 3 commands, 3 agents, 1 hook.

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 cadence-resume

README.md
[![agentmods](https://agentmods.dev/badge/skills/hxt9805/cadence/cadence-resume/github.svg)](https://agentmods.dev/skills/hxt9805/cadence/cadence-resume)
Your own site
<a href="https://agentmods.dev/skills/hxt9805/cadence/cadence-resume"><img src="https://agentmods.dev/badge/skills/hxt9805/cadence/cadence-resume/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 cadence-resume

Your own site · 80×15
<a href="https://agentmods.dev/skills/hxt9805/cadence/cadence-resume"><img src="https://agentmods.dev/badge/skills/hxt9805/cadence/cadence-resume.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,961 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 $0.00065 $0.02961
Opus 5 $0.00032 $0.01481
Sonnet 5 $0.00013 $0.00592
Haiku 4.5 $0.00006 $0.00296

Measured 11d ago against content hash e7d55256fcc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cadence-resume 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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (handoff_cleanup_helper.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/cadence-resume/SKILL.md · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cadence-resume(v0.4)

定位

用户跑 /cadence-resume 或说"继续上次" → 展示可 resume 的 handoff 列表 → 用户选择 → 加载对应 handoff 上下文 + 对比当前档案状态 → 报告"你上次讨论到哪、和现在有何差异"。

路径约定

所有 handoff 产物必须位于 <project-root>/cadence/.handoff/。不得在项目根创建或读取裸 .handoff/;Step 1 前置检测发现时只提示迁移,不阻断主流程。

流程

Step 1:列出可 resume 的 handoff

前置检测(路径漂移护栏)

读取 index 之前,先检测项目根是否存在裸 .handoff/(历史版本不一致 bug 痕迹):

  • 若 <project-root>/.handoff/ 存在 且 <project-root>/cadence/.handoff/ 不存在 → 一行提示: ⚠️ 检测到 .handoff/ 在项目根,这是 v0.2.0 历史路径不一致 bug 的痕迹。建议:mv .handoff cadence/.handoff 后重试。 本次仍按规范从 cadence/.handoff/ 读取(为空则展示"无 handoff")。
  • 若两者都存在 → 警告 ⚠️ 同时存在项目根 .handoff/ 和 cadence/.handoff/,请手动合并(以 cadence/.handoff/ 为准)。
  • 否则静默通过。

检测失败(IO 异常等)→ 不抛、不阻断主流程(参 § Step 6 失败优雅降级风格),继续 Step 1 主体。

主体

读 cadence/.handoff/index.json,按 created_at 倒序展示最近 N 条(默认 N=5):

最近 handoff:
  1. 2026-04-23 18:00  v0.3 Phase D handoff 联动重构
  2. 2026-04-20 12:00  阶段 B 深度审查(legacy v0.2.2)
  ...
要继续哪条?(输入编号 / "new" 开新 session)

Step 2:用户选择后读取 handoff 快照

Read cadence/.handoff/<handoff_id>.md,解析 frontmatter。

Step 3:识别版本(v0.4 / v0.3 / legacy v0.2.2)

# 伪代码(Claude 按逻辑执行,不跑真 python)
is_legacy = (
    "content_hashes" not in frontmatter
    and "item_counts" in frontmatter
)
  • 有 content_hashes + continuation_refs + fidelity → v0.4,走 Step 4a
  • 仅有 content_hashes → v0.3,走 Step 4a 的兼容路径
  • legacy v0.2.2 → 走 Step 4b

判据优先级:字段判据为主(覆盖 99% 场景);若字段判据两字段都不存在或都存在(corner case,如文件损坏或迁移中)→ 调用 python ${CLAUDE_PLUGIN_ROOT}/skills/cadence-handoff/scripts/validate_handoff.py <path>(macOS / Linux 把 python 换成 python3)兜底:v0.3 合法则走 4a;抛 "legacy v0.2.2 detected" 则走 4b;其他错误 → 告知用户"handoff 文件格式无法识别"。

Step 4a:v0.3/v0.4 — hashes 对比 + canonical 恢复

  1. 用 cadence-handoff Step 3 同方法(git hash-object 首选,平台 fallback 见 skills/cadence-handoff/SKILL.md Step 3)计算当前 cadence/_INDEX.md + _ACTIVE.md 的 sha1
  2. v0.4:逐个验证 continuation_refs.path 存在,计算当前 sha1 并与快照对比
  3. 读取所有校验通过的 continuation discussion,不得只展示路径而不读正文
  4. 仅依赖 handoff + 已读 cadence 档案回答冷启动六问:
    • 已决定什么?
    • 为什么?
    • 否决过什么?
    • 哪些约束不能破坏?
    • 哪些问题仍未决定?
    • 下一步是什么?
  5. 对比所有 hashes:

Read the full file on GitHub · 214 lines

Files

What ships with it

2 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. 11d ago First seen · 214 lines · 65 tokens per session scan A e7d55256fcc9

Subscribe to this mod's changes

cadence-resume is a skill published in the GitHub repository hxt9805/cadence (5 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 2,961 once invoked, about $0.0003 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.

Claude CodeMemory and contextcodexdev-toolspluginsession-managementworkflow
Related

Other skills, from other repositories

flow-next-audit

Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.

gmickel/flow-next · 46 tokens

flow-next-memory-migrate

Migrate legacy flat .flow/memory files to the categorized YAML schema. One-time ceremony. Use when asked to migrate flow memory.

gmickel/flow-next · 33 tokens

project-memory

Generate a project-specific context file from a brief so an AI assistant remembers your editorial constraints, voice, audience, and quality bar across sessions.

ur-grue/autopunk-media-skills · 31 tokens

bd-detox

Remove the anti-MEMORY.md clause from a project that already ran vanilla bd init, on the paths that actually reach Claude Code — the CLAUDE.md BEADS INTEGRATION block and bd's runtime bd prime output. Idempotent. Invoke as /ticket-flow:bd-detox (default: strip the clause, append the Coexistence Policy to CLAUDE.md…

keefar/ticket-flow · 0 tokens

Self-Improving + Proactive Agent

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when (1) a command, tool, API, or operation fails; (2) the user corrects you or rejects your work; (3) you realize your knowledge is outdated or incorrect; (4) you…

UnicomAI/wanwu · 105 tokens

ontology

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what…

UnicomAI/wanwu · 86 tokens