Agent skill
skill-usage-logger
All skill MUST use this logger to record usage events in NDJSON format.Log Codex skill usage events to NDJSON with safe concurrent appends.
Install this agent skill to your Project
npx add-skill https://github.com/shaowei-g/codex-skills/tree/main/skills/skill-usage-logger
SKILL.md
Skill Usage Logger
Overview
Provide a single logger script that any skill can call to append an NDJSON event to ~/.codex/skill-usage.ndjson, with concurrency-safe writes.
Quick Start
- Add a small logging note at the very top of a skill's
SKILL.mdso it is executed whenever that skill runs. - Call the logger once after successful completion, or immediately before aborting on error.
Use this snippet (edit <skill_name> and optional <meta_json>):
# Usage logging (call on success or error as appropriate)
~/.codex/skills/skill-usage-logger/scripts/log_skill_usage.sh \
--skill "<skill_name>" \
--status "success" \
--meta '<meta_json>'
If an error prevents completion, call with --status error and include useful --meta (e.g., reason or failing step).
Logger Script
- Path:
~/.codex/skills/skill-usage-logger/scripts/log_skill_usage.sh - Required args:
--skill <skill_name>--status <success|error>
- Optional args:
--meta <json_string>(must be valid JSON; included asmetain the event)
Output format (NDJSON)
Each call appends one line with at least:
{ "ts": "<ISO8601>", "skill": "<skill_name>", "status": "success|error" }
When --meta is provided and valid JSON, it is included as "meta": <json_value>.
Concurrency Notes
The script uses flock on ~/.codex/skill-usage.ndjson.lock to prevent interleaving when multiple skills log at the same time.
Example
~/.codex/skills/skill-usage-logger/scripts/log_skill_usage.sh \
--skill "frontend-design" \
--status "success" \
--meta '{"project":"landing-page","durationMs":1842}'
Resources
scripts/
log_skill_usage.sh: NDJSON logger with required parameters and concurrency-safe appends.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
ekoen-frontend-code-review
Production-grade code review for the eKoEN frontend codebase. Use when asked to review, audit, inspect, or harden eKoEN React/Next.js frontend code, pages, components, hooks, API clients, or state layers for bugs, performance bottlenecks, TypeScript safety issues, request inefficiency, state-management risks, memory leaks, rendering regressions, error-handling gaps, duplication, or maintainability problems, especially when a structured severity-ranked report with code locations, root causes, suggested fixes, and example refactors is required.
ekoen-backend.doc.route-error
Add HttpErrorRes responses to eKoEN backend routes when controllers can throw errors from app/util/errors/index.ts
conventional-commit-helper
Generate and validate Conventional Commit messages for semantic-release workflows. Use when a user asks to write a commit message, asks to commit changes, asks for commit type/scope selection, or asks to enforce Conventional Commits consistency.
codex-cli-subagent-transport
Use only when native subagent execution is unavailable and the caller needs one deterministic Codex CLI run with repo-local artifacts and a manifest-based result contract.
nodejs-package-json
Patch a Node.js project's package.json for standard build automation. Use when asked to add/standardize package.json scripts like prebuild/postbuild for TypeScript builds (rimraf dist + tsc-alias), adjust prebuild for Next.js (rimraf dist .next), or ensure an existing package.json pkg config includes required scripts/assets/targets/outputPath.
Didn't find tool you were looking for?