ccpm
Project management skill system for Agents that uses GitHub Issues and Git worktrees for parallel agent execution.
Runssource: GitHubhomepageShellMITcommit 7d7e4623bc6d
Shell, MIT licensed. The project labels itself: ai agents, ai coding, claude, claude code, project management and vibe coding.
ccpm runs. An Argusic agent installed it in 2.7 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
CCPM skill installed at /home/runner/.codex/skills/ccpm, .claude/ directory initialized with all subdirectories, gh 2.64.0 available via ~/.local/bin/gh, and all 14 local workflow scripts execute with correct output against real data. GitHub sync commands blocked by missing interactive auth.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- GitHub CLI (gh) not in PATH at start; sudo not available for apt-get install1.2 minutes
- GitHub authentication unavailable non-interactively in sandbox
- Install time
- 3 minutes
- Cold machine to finish
- 4 minutes
- Errors hit and fixed
- 2 hit, 2 fixed with no human help
- How the result was proved
- Ran all 14 bash scripts against sample PRD/epic/task data: status.sh (1 PRD, 1 epic, 3 tasks), standup.sh (standup report with correct counts), epic-list.sh (1 epic in-progress at 0%), epic-status.sh (3 tasks, 0% progress bar), epic-show.sh (3 parallel tasks listed), prd-list.sh (1 PRD in-progress), prd-status.sh (distribution chart), next.sh (3 ready tasks), blocked.sh (0 blocked), in-progress.sh (1 active epic), search.sh 'task' (4 matches across PRD + tasks), validate.sh (0 errors, 0 warnings, system healthy), help.sh (full command list), init.sh (structure created)
- Model tokens used
- 69,244
- Exact commit tested
- 7d7e4623bc6d
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
✅ System is healthy! EXIT: 0 All scripts verified successfully. Here's the final assessment: **Install**: The skill directory is properly structured. We installed the `gh` CLI by downloading t… **Verification**: All 14 bash scripts (`status.sh`, `standup.sh`, `epic-list.sh`, `epic-show.sh`, `… 2026-09-28T02:00:09.622946Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… 2026-09-28T02:00:09.622989Z ERROR codex_core::session: failed to record rollout items: thread 01a0e… tokens used 69,244 All scripts verified successfully. Here's the final assessment: **Install**: The skill directory is properly structured. We installed the `gh` CLI by downloading t… **Verification**: All 14 bash scripts (`status.sh`, `standup.sh`, `epic-list.sh`, `epic-show.sh`, `…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 2.7 minutes, faster than the median of the 25 comparable projects Argusic has measured.
- Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 26 ai-agents projects Argusic has installed and timed, ccpm was the 8th fastest to reach a running state, and 17 of 26 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 2.7 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
ai-agentsai-codingclaudeclaude-codeproject-managementvibe-coding
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ccpm)Questions
- Does ccpm run?
- Yes. ccpm runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test ccpm?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7d7e4623bc6d. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test ccpm?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ccpm take to install?
- 2.7 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does ccpm need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ccpm?
- 2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ccpm compare with the alternatives?
- Of the 26 ai-agents projects Argusic has installed and timed, ccpm was the 8th fastest to reach a running state, and 17 of 26 reached one at all.
- Where is the evidence for ccpm?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.