Not in the top 1,000 by GitHub stars
SnakeO/claude-co-commands
Co-* planning, validation, and brainstorming commands for Claude Code via Codex MCP
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugins/co-commands/skills/co-brainstorm/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
7c477b2bba4d → 7c477b2bba4d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 7c477b2bba4d
No earlier version was observed for comparison.
plugins/co-commands/skills/co-plan/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
7c477b2bba4d → 7c477b2bba4d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 7c477b2bba4d
No earlier version was observed for comparison.
plugins/co-commands/skills/co-validate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
7c477b2bba4d → 7c477b2bba4d
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 7c477b2bba4d
No earlier version was observed for comparison.
Verified commit 7c477b2bba4d6a7c416cd15f829dbf1d4ffd358a
git clone --filter=blob:none --no-checkout https://github.com/SnakeO/claude-co-commands.git .hotskills/snakeo-claude-co-commands && git -C .hotskills/snakeo-claude-co-commands checkout --detach 7c477b2bba4d6a7c416cd15f829dbf1d4ffd358a
# Copy each selected skill directory from .hotskills/snakeo-claude-co-commands into .claude/skills/<skill-name>/Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- co-brainstorm
plugins/co-commands/skills/co-brainstorm - co-plan
plugins/co-commands/skills/co-plan - co-validate
plugins/co-commands/skills/co-validate
How it works
co-brainstorm
When your agent uses it
Bounce ideas off Codex. Use when you want fast alternative ideas, critiques, and perspectives on any topic. Triggers an interactive conversation with Codex for brainstorming and exploration.
What it loads into context
Frontmatter
44 tokensAlways available to the agent
SKILL.md
1,163 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How Codex Is Reached
- Step 1: Start Codex and Hand It to a Background Subagent
- Step 2: Do Your Own Brainstorming
- Step 3: Retrieve and Compare
- Continuing the Conversation
- How to Treat Responses
Scripts executed separately
../../scripts/codex-session
Files
../../../../.claude-plugin/marketplace.jsonasset540 bytes../../scripts/codex-sessionruns3,823 bytesSKILL.mdcore5,031 bytesSKILL.mdcore5,031 bytes
Read SKILL.md
# Co-Brainstorm: Bounce Ideas Off Codex
## How Codex Is Reached
Codex runs through its CLI, driven by the helper script `scripts/codex-session`, which lives two
levels above this skill's base directory: call it as `<base directory>/../../scripts/codex-session`.
It keeps one Codex conversation per session folder and always runs Codex in its read-only sandbox:
- `codex-session new <label>` makes a session folder and prints its path
- `codex-session run <DIR>` sends `<DIR>/prompt.md` as the first message and waits for the reply
- `codex-session read <DIR>` prints Codex's latest reply
- `codex-session reply <DIR>` sends a follow-up read from stdin and prints the reply
Shell variables do not survive between Bash calls, so always use the literal folder path.co-plan
When your agent uses it
Generate a parallel plan via Codex. Use when you want an additional planning perspective to compare against your own plan. Runs in the background so you can continue working in parallel.
What it loads into context
Frontmatter
42 tokensAlways available to the agent
SKILL.md
1,106 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How Codex Is Reached
- Step 1: Start Codex and Hand It to a Background Subagent
- Step 2: Create Your Own Plan
- Step 3: Retrieve and Compare
- Continuing the Conversation
- How to Treat Responses
Scripts executed separately
../../scripts/codex-session
Files
../../scripts/codex-sessionruns3,823 bytesSKILL.mdcore4,645 bytesSKILL.mdcore4,645 bytes
Read SKILL.md
# Co-Plan: Generate a Parallel Plan via Codex
## How Codex Is Reached
Codex runs through its CLI, driven by the helper script `scripts/codex-session`, which lives two
levels above this skill's base directory: call it as `<base directory>/../../scripts/codex-session`.
It keeps one Codex conversation per session folder and always runs Codex in its read-only sandbox:
- `codex-session new <label>` makes a session folder and prints its path
- `codex-session run <DIR>` sends `<DIR>/prompt.md` as the first message and waits for the reply
- `codex-session read <DIR>` prints Codex's latest reply
- `codex-session reply <DIR>` sends a follow-up read from stdin and prints the reply
Shell variables do not survive between Bash calls, so always use the literal folder path.co-validate
When your agent uses it
Get a staff engineer review of your plan via Codex. Use when you want critical review feedback on a plan before finalizing it. Pass the path to the plan file as the argument.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
1,362 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Arguments
- How Codex Is Reached
- Step 1: Start Codex and Hand It to a Background Subagent
- Step 2: Do Your Own Review
- Step 3: Retrieve and Compare
- Continuing the Conversation
- How to Treat Responses
Scripts executed separately
../../scripts/codex-session
Files
../../scripts/codex-sessionruns3,823 bytesSKILL.mdcore5,898 bytesSKILL.mdcore5,898 bytes
Read SKILL.md
# Co-Validate: Get a Staff Engineer Review of Your Plan
## Arguments
`$ARGUMENTS` should be the path to the plan file. If not provided, check if there is a plan file from the current session (for example in `~/.claude/plans/` or the working directory).
## How Codex Is Reached
Codex runs through its CLI, driven by the helper script `scripts/codex-session`, which lives two
levels above this skill's base directory: call it as `<base directory>/../../scripts/codex-session`.
It keeps one Codex conversation per session folder and always runs Codex in its read-only sandbox:
- `codex-session new <label>` makes a session folder and prints its path
- `codex-session run <DIR>` sends `<DIR>/prompt.md` as the first message and waits for the replySkills included
- co-brainstorm
- co-plan
- co-validate
Repository facts
- License
- MIT
- Created
- Feb 9, 2026
- Last pushed
- Sep 28, 2026
- Forks
- 10
- Open issues
- 0
- Project activity
- Active
Before you install
Local scriptsAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 3 notes
plugins/co-commands/skills/co-brainstorm/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/co-commands/skills/co-plan/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/co-commands/skills/co-validate/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 2 network referencesin 1 file: .claude-plugin/marketplace.json:1
- No hidden or obfuscated text
- No instruction overrides
- 3 executable scriptsin 1 file: plugins/co-commands/scripts/codex-session:1
- No access to secrets
- No requests to vote in Hot
Show all 5 signals by file
.claude-plugin/marketplace.json
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 3 facts
- Executable script in code of a file that runsplugins/co-commands/scripts/codex-session:1High confidence
- Executable script in code of a file that runsplugins/co-commands/scripts/codex-session:1High confidence
- Executable script in code of a file that runsplugins/co-commands/scripts/codex-session:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md plugins/co-commands/skills/co-brainstorm/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/co-commands/skills/co-brainstorm/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/co-commands/skills/co-brainstorm/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/co-commands/skills/co-brainstorm/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/co-commands/skills/co-brainstorm/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
