Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
SkillScore73Maintained
Automatic
◆Coding pack
Last verified 8/20/2026
What it changes
Passed 13 of 18 test cases with the skill, and 6 of 18 without it.
Without skill32%
With skill73%
Checks it passed that the model alone missed
Provides concrete action notes summarizing added test cases
Delivers task execution results for the interface generation
Includes concrete action notes detailing the code changes made
and 13 more in the full report
9 fixed7 passed either way6 still failing0 broke
Pass-rate lift
+41 pp
Tokens
-8%
Agent turns
0%
Response time
-23%
Model gemini-3.6-flashMeasured 8/20/2026v116 of 22 cases passed with skill · 18 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
Avoid giving me pseudo-code or manual coding instructions. Run Codex CLI in a background process to create REST API stubs for `/v1/analytics` in our Express router, then share the outcome and action notes.
What was checked, without and with the skill
Checked
Without skill
With skill
Runs Codex CLI as a background process to implement Express REST API endpoints
Missed
Passed
Shares concrete action notes describing the created endpoint stubs
Missed
Passed
case-11 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md33 lines3 filesincludes scripts
Coding-agent
Purpose
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Routing
Use when: Use when the user asks to run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Do not use when: Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead. Avoid using in non-interactive environments unless automation can fully satisfy prompts.
Outputs: Outcome from Coding-agent: task-specific result plus concrete action notes.
Success criteria: Returns concrete actions and decisions matching the requested task, with no fabricated tool-side behavior.
Trigger Examples
Positive
Use the coding-agent skill for this request.
Help me with coding-agent.
Use when the user asks to run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Coding-agent: provide an actionable result.
Negative
Do not use when the request is asking for planning documents, high-level strategy, or non-executable discussion; use the relevant planning or design workflow instead. Avoid using in non-interactive environments unless automation can fully satisfy prompts.
Do not use coding-agent for unrelated requests.
This request is outside coding-agent scope.
This is conceptual discussion only; no tool workflow is needed.
Runtime Prompt
Current runtime prompt length: 982 characters.
Runtime prompt is defined directly in ../coding-agent.json.