Csharp Async
github/awesome-copilot
Get best practices for C async programming. An agent skill from github/awesome-copilot.
Inspect Codex async task progress from the correct data directory.
MITAuto-check passed
Install Codex Task Inspector
$ npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install bifrost-proxy/bifrost codex-task-inspector --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/bifrost-proxy/bifrost.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/codex-task-inspector .claude/skills/codex-task-inspector && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "codex-task-inspector" agent skill from https://github.com/bifrost-proxy/bifrost/tree/main/.agents/skills/codex-task-inspector into .claude/skills/codex-task-inspector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-task-inspector", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/bifrost-proxy/bifrost/tree/main/.agents/skills/codex-task-inspectorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install bifrost-proxy/bifrost codex-task-inspector --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bifrost-proxy/bifrost.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/codex-task-inspector .agents/skills/codex-task-inspector && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "codex-task-inspector" agent skill from https://github.com/bifrost-proxy/bifrost/tree/main/.agents/skills/codex-task-inspector into .agents/skills/codex-task-inspector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-task-inspector", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install bifrost-proxy/bifrost codex-task-inspector --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bifrost-proxy/bifrost.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/codex-task-inspector .cursor/skills/codex-task-inspector && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "codex-task-inspector" agent skill from https://github.com/bifrost-proxy/bifrost/tree/main/.agents/skills/codex-task-inspector into .cursor/skills/codex-task-inspector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-task-inspector", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/bifrost-proxy/bifrost.git --path .agents/skills/codex-task-inspector--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install bifrost-proxy/bifrost codex-task-inspector --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bifrost-proxy/bifrost.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/codex-task-inspector .gemini/skills/codex-task-inspector && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "codex-task-inspector" agent skill from https://github.com/bifrost-proxy/bifrost/tree/main/.agents/skills/codex-task-inspector into .gemini/skills/codex-task-inspector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-task-inspector", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install bifrost-proxy/bifrost codex-task-inspectorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/bifrost-proxy/bifrost.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/codex-task-inspector .github/skills/codex-task-inspector && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "codex-task-inspector" agent skill from https://github.com/bifrost-proxy/bifrost/tree/main/.agents/skills/codex-task-inspector into .github/skills/codex-task-inspector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-task-inspector", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install bifrost-proxy/bifrost codex-task-inspector --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/bifrost-proxy/bifrost.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/codex-task-inspector .opencode/skills/codex-task-inspector && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "codex-task-inspector" agent skill from https://github.com/bifrost-proxy/bifrost/tree/main/.agents/skills/codex-task-inspector into .opencode/skills/codex-task-inspector/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-task-inspector", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
codex-task-inspector- GitHub stars
- 160
- Token cost
- ~1.3k tokens
- SKILL.md length
- 269 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
Inspect Codex async task progress from the correct data directory.
- Works in 4 steps: 本地 Codex 进程 → 任务产物摘要 → CI 状态 → …
- The user asks to check Codex status
- SKILL.md covers 关键纠错（高频踩坑）, 适用场景, 核心原则 and 标准检查顺序, plus 3 more sections
- Runs Python scripts from its folder; calls python3
What it does
Codex Task Inspector is an agent skill from bifrost-proxy/bifrost. Inspect Codex async task progress from the correct data directory. Use when the user asks to check Codex status, inspect async task progress, summarize task state, or determine whether local Codex workers are still running. Always detect the active Codex data dir first: prefer CODEXHOME when set, otherwise fall back to $HOME/.codex; only use repo .codex-tasks when the user explicitly targets it.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/detect_codex_data_dir.py`).
The repository describes itself as: Bifrost 是一个用 Rust 编写的高性能、AI 友好的代理服务器，它提供强大的请求拦截、修改和规则配置能力，支持 TLS 解密、脚本扩展等高级功能，支持强大的模糊搜索，支持导入导出分享，支持一键重放请求，支持Coding Agent 自主管理。提供类似 postman 的请求管理和验证能力，无缝和代理能力集成。 The licence is MIT.
When your agent uses it
- The user asks to check Codex status
- Inspect async task progress
- Summarize task state
- Determine whether local Codex workers are still running
Example prompts
- “/codex-task-inspector”
Requirements
- Python 3
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 019b7a4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Codex Task Inspector loads about 1.3k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 269 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from bifrost-proxy/bifrost at commit 019b7a4, republished under its MIT licence (© bifrost-proxy). 269 words, ~1,340 tokens.
Download SKILL.mdSave it as
.claude/skills/codex-task-inspector/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- codex-task-inspector
- description
- Inspect Codex async task progress from the correct data directory. Use when the user asks to check Codex status, inspect async task progress, summarize task state, or determine whether local Codex workers are still running. Always detect the active Codex data dir first: prefer CODEX_HOME when set, otherwise fall back to $HOME/.codex; only use repo .codex-tasks when the user explicitly targets it.
Codex Task Inspector
用于统一检查 Codex 异步任务状态，避免把“仓库里的任务跟踪文件（.codex-tasks/）”与“Codex 实际数据目录里的 session/rollout 日志”混为一谈。
关键纠错（高频踩坑）
当用户提供类似 019df414-... 这种 rollout/session id 并询问“任务进展”，默认应优先检查探测出的 Codex 数据目录：
- ✅
<detected_codex_dir>/sessions/YYYY/MM/DD/rollout-...-<id>.jsonl（权威事实来源：含 task_complete、命令执行、CI watch 记录） - ⚠️
.codex-tasks/只在用户明确说“看仓库里的 .codex-tasks 跟踪”或你确定该任务是由仓库派发器写入.codex-tasks/时才用
如果你先去 .codex-tasks/ 导致找不到 id，这是误判路径；应立即切换到探测出的 Codex 数据目录再查。
适用场景
当用户提到以下意图时触发：
- “检查 Codex 状态”
- “看看 Codex 任务进展”
- “汇总
.codex-tasks” - “本地任务还在跑吗”
- “CI 这边还剩什么”
- “哪个 Codex 任务失败了”
核心原则
- 先判定本地进程，再看文件产物。 不要因为
.codex-tasks里还有文件，就误判任务仍在运行。 - 本地任务状态与 CI 状态分开汇报。
.pid代表本地进程，*-last.md/*-report-*.md代表任务产物，*.log里的 poll 代表 CI 轮询。 - 默认只读。 不修改
.codex-tasks/，不清理 pid/log/report，不擅自重跑任务。 - 输出必须给出下一步建议，但只限于：继续查失败原因 / 整理状态表 / 指定某任务深挖。
标准检查顺序
第 0 步：先选对数据目录（必须）
0.0 先探测 Codex 实际数据目录
无论最终是否会落到 .codex-tasks/，先明确当前机器上的 Codex 数据目录，避免把 ~/.codex 当成硬编码事实。
优先运行：
python3 .agents/skills/codex-task-inspector/scripts/detect_codex_data_dir.py解读规则：
selected_source=env:CODEX_HOME→ 说明当前应优先看CODEX_HOMEselected_source=default:$HOME/.codex→ 说明当前使用默认回退目录markers里若存在config_toml/sessions_dir/session_index/history/state_db，可作为“这是活跃 Codex home”的旁证
只有当用户明确要求检查仓库 .codex-tasks/ 时，才切换到仓库路径；否则都先以探测结果为准。
输入信号 → 选路由：
- 用户给的是
019...这种 rollout/session id，或明确说“去 Codex 默认数据目录” → 走探测出的 Codex 数据目录 - 用户明确说“看这个仓库
.codex-tasks” → 走.codex-tasks/
0.1 在探测出的 Codex 数据目录按 rollout/session id 定位日志
优先在 <detected_codex_dir>/sessions/ 下找 rollout-*-<id>.jsonl：
export RID='019df414-235e-74e3-be4b-84f883e0ea17'
export CODEX_DIR="$(python3 .agents/skills/codex-task-inspector/scripts/detect_codex_data_dir.py | python3 -c 'import json,sys; print(json.load(sys.stdin)["selected_path"])')"
python3 - <<'PY'
import glob
import os
rid = os.environ['RID']
base = os.path.join(os.environ['CODEX_DIR'], 'sessions')
paths = glob.glob(f"{base}/**/rollout-*-{rid}.jsonl", recursive=True)
for p in sorted(paths):
print(p)
PY若直接匹配不到，可扩大为内容扫描（注意控制扫描数量，按 mtime 取最近 N 个文件即可）。
0.2 从 jsonl 里读最终结论
优先寻找最终完成事件；当前 rollout 日志里常见形态是：
event_msg.payload.type == "task_complete"- 或等效的最终完成记录
其中的 last_agent_message 是最直接的任务总结；如需“是否仍在跑”，看最后的事件时间戳 + 是否还有后续 exec_command_*。
第一步：检查本地 Codex 进程
如果走 .codex-tasks/ 路径：先看 .codex-tasks/*.pid，逐个用 ps 判断进程是否仍存活。
推荐命令：
python3 - <<'PY'
import os, glob, subprocess
for path in sorted(glob.glob('.codex-tasks/*.pid')):
name = os.path.basename(path)
with open(path) as f:
pid = f.read().strip()
if not pid.isdigit():
print(f'{name}\t{pid}\tINVALID_PID')
continue
p = subprocess.run(
['ps', '-p', pid, '-o', 'pid=,etime=,state=,ppid=,command='],
capture_output=True,
text=True,
)
line = ' '.join(p.stdout.split()) if p.stdout.strip() else 'NOT_RUNNING'
print(f'{name}\t{pid}\t{line}')
PY判定规则：
- 只要
ps没有返回进程行，就记为NOT_RUNNING - 如果所有 pid 都是
NOT_RUNNING，必须明确告诉用户：- 本地 Codex 异步任务当前没有在运行
- 如果存在存活进程，再单独列出活跃项
第二步：检查任务产物结论
优先看最近的 *-last.md：
python3 - <<'PY'
from pathlib import Path
base = Path('.codex-tasks')
files = sorted(base.glob('*-last.md'), key=lambda p: p.stat().st_mtime, reverse=True)
for p in files[:10]:
text = p.read_text(errors='ignore')
first_nonempty = next((line.strip() for line in text.splitlines() if line.strip()), '')
print(f'=== {p.name} ===')
print(first_nonempty[:200])
print()
PY必要时补充：
*-report-*.md：查看最终报告*.jsonl/*.meta：只在需要确认任务上下文时再读
关注点：
- 是否已经“已完成”
- 是否有明确阻塞原因（例如 push 失败、网络解析失败、CI 失败）
- 是否已经产出了报告文件路径
第三步：检查 CI 轮询状态
如果 .codex-tasks/ 下存在 *.log，优先检查与当前话题最相关的 poll log。
例如读取最后几十行：
tail -n 40 .codex-tasks/skill-creator-ci-poll.log或按需读取尾部：
python3 - <<'PY'
from pathlib import Path
p = Path('.codex-tasks/skill-creator-ci-poll.log')
if p.exists():
lines = p.read_text(errors='ignore').splitlines()
for line in lines[-40:]:
print(line)
PY关注分类：
completed/successcompleted/failurein_progress/pendingqueued/pending
如果看到失败项：
- 必须单独列出失败 job 名称
- 不要把它和“本地 Codex 任务还在运行”混为一谈
推荐输出结构
回答时固定分四段：
1. 本地 Codex 进程
- 是否有本地活跃进程
- 哪些 pid 已停止 / 仍运行
2. 任务产物摘要
- 最近几个
*-last.md的结论 - 是否已有报告、是否有阻塞原因
3. CI 状态
- 当前仍在跑的 job
- 已失败的 job
- 已完成的关键 job（只列核心，不必全抄）
4. 下一步建议
默认只给这类建议：
- “继续查某个失败 job 的原因”
- “把
.codex-tasks整理成状态表” - “展开某个具体任务报告”
禁止事项
- 不要因为
.codex-tasks文件存在就说“任务还在跑” - 不要先读一堆 report 再去确认 pid
- 不要把 CI poll log 当成本地任务进程状态
- 不要默认替用户清理
.codex-tasks - 不要直接建议“修代码”或“重跑任务”，除非用户明确要求
最小结论模板
如果本地进程全停、CI 仍在跑且有失败项，优先用类似结构：
- 本地 Codex：没有正在运行的任务
- 任务产物：最近若干任务已完成/有报告，某任务存在阻塞原因
- CI：还有若干 job 在跑，且某个 job 已失败
- 下一步：可以继续查失败原因，或者整理状态表© bifrost-proxy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (scripts) in .agents/skills/codex-task-inspector of bifrost-proxy/bifrost.
- SKILL.md
- scripts/detect_codex_data_dir.py
Open the folder on GitHubat commit 019b7a4
Compare with similar skills
Codex Task Inspector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Codex Task Inspector this skillbifrost-proxy/bifrost | 160 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Csharp Asyncgithub/awesome-copilot | 40k | 2 repos | ~466 | Automated safety check: Pass | MIT | |
| Correctcursor/plugins | 10k | 3 repos | ~612 | Automated safety check: Pass | None | |
| CorrectionNxcoreAI/EverRoom | 3k | — | ~290 | Automated safety check: Pass | Custom licence | |
| Asynconsi/gomega | 2.4k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Progressive Jpegthedaviddias/Front-End-Checklist | 74k | — | ~426 | Automated safety check: Pass | MIT |
Similar skills
- Official
- Official
Correct
cursor/plugins
Find the mistakes agents keep repeating in this repo and make each one impossible.
Correction
NxcoreAI/EverRoom
Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.
Async
onsi/gomega
Polling assertions in Gomega — Eventually (poll until it passes) and Consistently (must keep passing), the func(g Gomega) callback idiom, WithTimeout/WithPolling/Within/ProbeEvery, WithContext and…
Progressive Jpeg
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing image assets, markup, and CDN or build transforms related to Use progressive JPEG encoding.
Defer Async
thedaviddias/Front-End-Checklist
A skill your agent uses when reviewing templates, rendered HTML, or shared components related to Load scripts with defer, async, or type=module.
More from bifrost-proxy/bifrost
All 9 skills in this repoJuejin Publish
bifrost-proxy/bifrost
Publish Markdown articles and Bifrost capability series to Juejin, or verify with Microsoft Edge that a published Juejin page's title and body match the local Markdown.
Site Cookie Login
bifrost-proxy/bifrost
Open a target website, wait for user login, verify login with required cookies plus an HTTP probe, and save cookies into .env for later automation.
Zhihu Publish
bifrost-proxy/bifrost
Publish Markdown articles to Zhihu Columns through authentication context recovered locally from Bifrost traffic and a built-in publish payload schema, save drafts, prevent duplicate posts, and…
E2E Verify
bifrost-proxy/bifrost
面向 Bifrost 管理端的端到端 UI 与 API 验证工具. An agent skill from bifrost-proxy/bifrost.
GitHub Actions Pat
bifrost-proxy/bifrost
用 Personal Access Token 通过 GitHub REST API 分析 Actions CI 的失败 run/job/step、拉取日志、轮询运行状态、做 PR code review，并驱动 fix → push → watch → iterate 的闭环。Token 只从 GITHUBTOKEN 环境变量读取，不落盘、不回显。适合在 bifrost remote /…
Design Md
bifrost-proxy/bifrost
A skill your agent uses when changing Bifrost WebUI, desktop shell UI, public site, docs visual style, interaction patterns, layout, copy density, colors, typography, spacing, or component styling.
Questions about Codex Task Inspector
What does Codex Task Inspector do?
Inspect Codex async task progress from the correct data directory. Codex Task Inspector is an agent skill from bifrost-proxy/bifrost. Inspect Codex async task progress from the correct data directory.
When should I use Codex Task Inspector?
Codex Task Inspector fits situations like: the user asks to check Codex status; inspect async task progress; summarize task state; determine whether local Codex workers are still running.
How do I install Codex Task Inspector in Claude Code?
Run `npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a claude-code`. Or copy the skill folder (.agents/skills/codex-task-inspector in bifrost-proxy/bifrost) into .claude/skills/codex-task-inspector in your project. Claude Code loads it when a task matches its description.
How do I install Codex Task Inspector in Codex?
Run `npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a codex`. Or copy the skill folder (.agents/skills/codex-task-inspector in bifrost-proxy/bifrost) into .agents/skills/codex-task-inspector in your project. Codex loads it when a task matches its description.
Can I use Codex Task Inspector in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add bifrost-proxy/bifrost --skill codex-task-inspector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-task-inspector, .gemini/skills/codex-task-inspector, .github/skills/codex-task-inspector and .opencode/skills/codex-task-inspector in your project.
What does Codex Task Inspector need to run?
Going by SKILL.md and its folder, Codex Task Inspector needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Codex Task Inspector access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Codex Task Inspector safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Codex Task Inspector use?
Codex Task Inspector is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Codex Task Inspector use?
About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Codex Task Inspector?
Skills that share tags, products or a category with Codex Task Inspector: Csharp Async (github/awesome-copilot, 40k stars), Correct (cursor/plugins, 10k stars), Correction (NxcoreAI/EverRoom, 3k stars) and Async (onsi/gomega, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Codex Task Inspector?
bifrost-proxy (a GitHub user) maintains it in bifrost-proxy/bifrost, which has 160 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 6, 2026.
Source: bifrost-proxy/bifrost on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.