sessions
Skill0 starsChanged 6 months agoMITView on GitHub
一条命令出 session 现状 + ROI 全景 HTML(包装 cc_sessions.py index + regen_dev_roi.py,输出规范 /debrief 风 HTML,含 vault nav + KPI clickable + per-project 表)。用户说「列会话 / session 现状 / 会话 ROI / sessions / /sessions / 看下 session / 清理候选」时触发
24 other projects use a version of this.
Adopted by
Most recently taken up by
- EthanLLL/loomtheir own version, first seen Nov 8, 2026
- Mereithhh/very-happytheir own version, first seen Nov 6, 2026
- microsoft/vscodetheir own version, first seen Nov 2, 2026
- griffinhilly/claude-code-synthesistheir own version, first seen Nov 1, 2026
- phnx-labs/agi-clitheir own version, first seen Oct 26, 2026
- phnx-labs/.agentstheir own version, first seen Oct 11, 2026
Used with
Projects with it also use tool-rename-deprecation, add-policy and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
gitpod-ioSkilltool-rename-deprecation
Ensure renamed built-in tool references preserve backward compatibility. Use when renaming a toolReferenceName, tool set referenceName, or any tool identifier. Run on ANY change to tool registration code. Covers legacyToolReferenceFullNames for tools and legacyFullNames for tool sets.
Also in 5 projects that use this
OpenCortexIDESkilladd-policy
Use when adding, modifying, or reviewing VS Code configuration policies. Covers the full policy lifecycle from registration to export to platform-specific artifacts. Run on ANY change that adds a `policy:` field to a configuration property.
Also in 4 projects that use this
gitpod-ioSkillagent-sessions-layout
Agent Sessions workbench layout — covers the fixed layout structure, grid configuration, part visibility, editor modal, titlebar, sidebar footer, and implementation requirements. Use when implementing features or fixing issues in the Agent Sessions workbench layout.
Also in 3 projects that use this
slopusSkillmetrics-graphana
Query and manage Grafana dashboards and Prometheus metrics for Happy infrastructure. Covers grafanactl CLI usage, direct Prometheus queries through Grafana proxy, and dashboard-as-code workflows. Use when user asks about metrics, dashboards, monitoring, Grafana, Prometheus, or wants to add/modify panels.
Also in 3 projects that use this
slopusSkillcontrol-flow
Analyze and design control flows and data structures. Produces compact ASCII tree diagrams showing triggers, call chains, payload shapes, state mutations, and re-render effects. Use when user asks to diagram, trace, visualize, or design a flow or data structure.
Also in 3 projects that use this
TheKREATORSSkillrefactor-clean
No description
Also in 3 projects that use this
- +2 more from gitpod-io
Other versions24 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 24
- microsoft/vscode★ 195ksame name
- slopus/happy★ 25ksame name
- gitpod-io/openvscode-server★ 6.2ksame name
- posit-dev/positron★ 4.3ksame name
- NeuralInverse/neuralinverse★ 221same name
- OpenCortexIDE/cortexide★ 175same name
- Altman-conquer/agentrejoin★ 75same name
- griffinhilly/claude-code-synthesis★ 67same name
- elijahmuraoka/skills★ 58same name
- phnx-labs/agi-cli★ 26same name
14 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- debriefSkill
- dispatchSkill
- dwsSkill
- file-cleanupSkill
- html-figSkill
- pdf-decryptSkill
- retro-digestSkill
- shipSkill
- spikeSkill
- verify-dataSkill
The file
Files
/sessions — Session 现状 + ROI 一站式 HTML
核心用途
一站式查看 ~/.claude/projects/**/*.jsonl 现状(数量、cwd、stale 程度、ROI),自动产规范富 HTML 给用户看。不要手工写 session 清单,走本 skill。
执行 3 步
- 刷索引:
uv run python3 ~/Dev/tools/dev/scripts/tools/cc_sessions.py index→ 写 runtime 索引 session_index.json 到 ~/.claude/projects/(全 jsonl 扫一遍) - 生成 HTML:
uv run python3 ~/Dev/tools/dev/scripts/tools/regen_dev_roi.py→ 重生~/Dev/wiki/handoffs/dev/dev-sessions-roi.html - 打开:
open ~/Dev/wiki/handoffs/dev/dev-sessions-roi.html
不重复执行的判定
若 dev-sessions-roi.html mtime < 5 分钟 且 无新 jsonl session 加入(find ~/.claude/projects -name '*.jsonl' -newer dev-sessions-roi.html | head -1 空)→ 跳过步骤 1+2,直接 open。
HTML 必含(验收点)
per [[user-facing-output-is-html]] [[html-must-be-vault-citizen]] [[every-number-card-must-be-clickable]]:
- vault nav 顶栏 + 侧边 aside 入口(_index / handoffs / topics)
- KPI 卡 clickable:session 总数、stale > 30d、top ROI、清理候选数 — 每个数字
<a href>指向锚点 - per-project 表:cwd 路径 + session count + last_ts + topic(完整 36 位 UUID 可粘贴
claude -r <uuid>) - Top ROI 段:按 turns × signal_density desc
- Stale 清理候选:stale_days desc,列出可归档
- 底部 backlinks + footer 时间戳
验收
- audit dead link = 0
<aside>+<nav>标签存在- 0 个裸
[[wikilink]](必解析为<a>) - KPI 数字全 clickable(每个 KPI card 内含
<a class="kpi">或 nested-in-anchor)
相关脚本 / skill 互补
| 入口 | 用途 | 与本 skill 关系 |
cc_sessions.py export <uuid> | 单会话导 markdown | 互补,不冲突 |
cc_sessions.py index | 刷 session_index.json | 本 skill 步骤 1 |
regen_dev_roi.py | 数据 + HTML 渲染引擎 | 本 skill 步骤 2 |
/debrief | 单会话 wrap-up HTML | 不同语境(debrief = 收尾 1 个,sessions = 俯瞰 N 个) |
/wrap recap | 会话复盘 md | 不同语境 |
反模式
- 直接手写 session 清单 HTML(绕过 regen_dev_roi.py,破坏 SSOT)
- 只跑
cc_sessions.py不出 HTML(用户要看 HTML,不要看 jsonl 字段) - 列会话只给 8 位短码(违反 [[session-listing-format]] — 必须完整 36 位 UUID + cwd + topic)
- 跑 regen 不验 dead link / 不验 vault citizen(HTML 退化)
触发短语
/sessions、列会话、session 现状、会话 ROI、看下 session、清理候选、cc session 全景
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

