skill CX Codex

run-history — Claude Code skill: run history and installation

Q: How do I install run-history in Claude Code?

Run `npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill run-history -a claude-code`. The skill file is at `~/.claude/skills/run-history/SKILL.md`.

Inspect CCAM runs, check whether a process is still active, and connect a live run to a saved Claude Code or Codex session.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill run-history -a claude-code

Open on GitHub

What run-history does

The skill searches CCAM run history and separates active processes from completed runs, failures, and records whose in-memory handle has been cleared. Filter entries by provider, working directory, model, status, or session ID. It returns run and session details, timestamps, lifecycle state, and a safe next action.

For a live handle, it uses ccam run get <id> --envelopes; saved sessions can be inspected with ccam session <session-id> and transcript tools. Resume is recommended only when a native session ID exists and the selected provider supports that session. Without both conditions, resuming is not established as a safe option.

What it helps with

find an earlier task by provider or session ID
check whether a process is active or finished
tell a failed run from one with usable output
match a live run to its saved agent session
choose whether to resume, inspect, or relaunch a task

Example prompts for the agent

Find the run for this working directory and report its status.
Inspect run abc123 and the session connected to it.
Check whether this task can be resumed safely or should be relaunched.

How to install run-history

1Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill run-history -a claude-code

2Manually: put the files in place

~/.claude/skills/run-history/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/run-history/

1Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill run-history -a codex

2Manually: put the files in place

.agents/skills/run-history/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill run-history -a cursor

2Manually: put the files in place

.cursor/skills/run-history/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install hoangsonww/Claude-Code-Agent-Monitor run-history

2Manually: put the files in place

.github/skills/run-history/SKILL.md

1Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill run-history -a gemini-cli

2Platform CLI

gemini skills install https://github.com/hoangsonww/Claude-Code-Agent-Monitor --path plugins/ccam-runner/skills/run-history

Manually: put the files in place

.devin/skills/run-history/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill run-history -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about run-history

How do I install run-history in Claude Code?

Run npx skills add hoangsonww/Claude-Code-Agent-Monitor --skill run-history -a claude-code. The skill file is at ~/.claude/skills/run-history/SKILL.md.

What does run-history do?

It inspects CCAM run records, checks process state, and relates live runs to saved Claude Code or Codex sessions.

When does run-history recommend resuming a session?

Only when a native session ID is available and the chosen provider supports that session.

Source text

SKILL.md · MIT

---
name: run-history
description: >
  Inspect CCAM dashboard-run history and relate live run handles to persisted
  Claude Code or Codex sessions. Use when finding a prior launched task,
  checking whether a run is still attached, reviewing start/end status, or
  deciding whether to resume, view, or relaunch work.
---

# Run History

1. Run `ccam run history --limit 100`.
2. Filter by provider, working directory, model, status, and session ID.
3. For a live handle, run `ccam run get <id> --envelopes`.
4. For the persisted agent session, use `ccam session <session-id>` and the
   session transcript tools.
5. Distinguish:
   - process still live
   - process completed with usable output
   - process failed
   - history row exists but the in-memory handle was reaped
6. Recommend resume only when the native session ID is present and the selected
   provider supports that session.

Return the exact run ID, provider, session ID, working directory, model,
timestamps, lifecycle state, and the next safe action.

setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. 1,052,851installs ask-matt Matt Pocock Routes you to the right Matt Pocock skill or flow for the task at hand. Use it when you need a starting point for a feature, prototype, incoming issue, or hard bug. 766,587installs to-tickets Matt Pocock Turns a plan, spec, or conversation into small end-to-end tickets with explicit blockers. Use it to agree on the work breakdown before tickets go to a tracker. 711,230installs writing-plans Jesse Vincent This skill turns requirements for a multi-step task into an implementation plan before code changes begin. It helps when another engineer needs exact files, interfaces, and checks. CX Codex 282,859installs caveman-review JuliusBrussee Turns code review comments into one line per finding: location, problem, fix. Useful when a diff or PR needs a fast pass without the filler. CX Codex +1 411,800installs caveman-compress JuliusBrussee Compresses CLAUDE.md, todo lists, and other prose files into a shorter format while retaining a readable backup. CX Codex +1 411,500installs

From the same set60