Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ValorVie/custom-skills --skill work-log-codexgit clone --depth 1 https://github.com/ValorVie/custom-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/valorvie/custom-skills/work-log-codex)<a href="https://agentmods.dev/skills/valorvie/custom-skills/work-log-codex"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/work-log-codex/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/valorvie/custom-skills/work-log-codex"><img src="https://agentmods.dev/badge/skills/valorvie/custom-skills/work-log-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.02156 |
| Opus 5.5 | $0.00027 | $0.00862 |
| Sonnet 5.5 | $0.00014 | $0.00431 |
| Haiku 4.5 | $0.00007 | $0.00216 |
Grade A, and why
work-log-codex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 16d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Log Codex
根據本機的 Codex 與 Claude Code 工作階段紀錄,產生可讀、可保存、可追溯的工作日誌。
使用時機
Use this skill when the user wants to:
- 針對
今天、昨天、本週或自訂日期區間整理工作日誌 - 想知道某段時間做了哪些專案、主要交付與研究內容
- 想把對話紀錄與 git 歷史整理成可讀的 Markdown 日誌
- 想輸出到本機
docs/work-logs/或 Obsidian
流程
這個 skill 的最佳路徑是 有界 parser -> 專案層任務摘要 -> 最終整合 -> 分層 formatter。
1. 解析時間範圍
支援:
todayyesterdaythis-weekthis-monthYYYY-MM-DDYYYY-MM-DD YYYY-MM-DD
可選輸入:
--project <name>:只看單一專案--output/--format:控制輸出方式
2. 執行有界 parser
使用 uv Python 3.14。parser 會在 stderr 顯示讀取與分析進度;stdout 只輸出 JSON。 在共用主機上一次只跑一個 parser。多個相鄰週次使用一個合併日期範圍,完成後再分週整理, 不要平行掃描同一批工作階段。
SKILL_DIR="$PWD/.agents/skills/work-log-codex"
PYTHONPATH="$SKILL_DIR" uv run --python 3.14 python -m wl_parser.work_log_parser \
TIME_RANGE \
[END_DATE] \
--timezone "Asia/Taipei" \
[--project "PROJECT"] \
--claude-home <absolute-claude-home> \
--codex-home <absolute-codex-home> \
--emit-project-dir /tmp/wl_projects \
> /tmp/wl_report.json
資料收集器只保留日期範圍內事件,並壓縮分析所需的 raw 欄位。若 stderr 長時間停在同一
階段、超出目前任務的時間或記憶體門檻,停止該次執行並保留量測,不要以多個 parser 重試。
3. 逐專案摘要
不要直接把整份 /tmp/wl_report.json 全讀進上下文。優先讀:
/tmp/wl_projects/manifest.json- 每個 project bundle JSON
prompts/project_summary.md
每個專案各做一次摘要,將相關 commit 與工作階段合併成 2 至 5 個任務。每個任務固定使用:
- **一行重點:** <一句可獨立閱讀的工作重點>
- **重點脈絡:** <300 字以內,說明起因、處理、結果與證據邊界>
- **來源:** <正式文件路徑及/或 repo@commit>
摘要規則:
- 優先從
git_commits理解實際交付主題 - 用
session_summaries補足未提交、研究、規劃中的工作 session_hints只當快速導覽,真正判讀以session_summaries為主- 合併 related commits,不要逐 commit 轉寫
- 沒有 commit 或正式文件時,明確標成研究/規劃,來源寫「工作階段摘要(無 Git commit)」
- 來源必須直接支持相鄰主張;不要把原始 session JSONL 當成正式完成證據
- 每段重點脈絡以 Unicode 字元數量測,不超過 300 字
- Token 成本不是主要限制;必要時可以逐專案、多次呼叫 AI 做摘要,不要為了省 token 犧牲語意品質
將每個專案摘要暫存到 /tmp/wl_project_<name>.md。
4. 生成最終摘要前段
讀取:
/tmp/wl_report.json的summary- 所有
/tmp/wl_project_<name>.md prompts/final_summary.md
產出 /tmp/wl_summary.md,內容必須只有:
### 當日總結### 逐專案摘要
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/report-template.md 248 B
- prompts/final_summary.md 1.1 KB
- prompts/project_summary.md 1.9 KB
- references/report-schema.md 2.1 KB
- references/sources.md 1.9 KB
- scripts/__init__.py 38 B runs code
- scripts/generate_work_log.py 12 KB runs code
- scripts/normalize.py 19 KB runs code
- scripts/render.py 13 KB runs code
- scripts/source_claude.py 6.9 KB runs code
- scripts/source_codex.py 10.0 KB runs code
- tests/fixtures/claude_sample/projects/-Users-arlen-projects-repo-b/repo-b-session.jsonl 473 B
- tests/fixtures/codex_sample/sessions/2026/03/11/rollout-sample.jsonl 521 B
- tests/test_claude_source.py 4.5 KB runs code
- tests/test_cli_smoke.py 5.5 KB runs code
- tests/test_codex_source.py 6.7 KB runs code
- tests/test_formatters.py 11 KB runs code
- tests/test_git_collector.py 2.3 KB runs code
- tests/test_parser.py 18 KB runs code
- wl_parser/__init__.py 62 B runs code
- wl_parser/formatters.py 14 KB runs code
- wl_parser/git_collector.py 4.4 KB runs code
- wl_parser/work_log_parser.py 32 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 16d ago Changed · +10 lines · +1 tokens per session d3f8c94c90a3
- 1mo ago First seen · 172 lines · 67 tokens per session scan A 2e1378f150e8
work-log-codex is a skill published in the GitHub repository ValorVie/custom-skills (5 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 2,156 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
onboard
Onboarding doc for a new contributor or agent — project state, conventions, priorities relevant to the specified role.
cron-task-creator
A scheduler for recurring octo agent tasks. Each task contains a schedule and a prompt, so octo can run an agent turn automatically at the specified times.
workflow-creator
Turn a repeatable multi-step task into a runnable, reusable saved workflow through guided conversation, in either of two shapes — chaining existing skills/recordings (wiring each one's output into the next's input), or composing the workflow script's own primitives (agent/parallel/pipeline) directly when the task…
resume-crafting
A career-writing aid for turning a résumé or cover letter into clear evidence of results. It uses measurable outcomes and adapts the wording to a job description and applicant-tracking systems, or ATS tools that scan applications for relevant terms.
batch-file-ops
Batch-Dateioperationen (Löschen, Verschieben, Kopieren, Auflisten) mit Glob-Mustern. CLI-Werkzeug für effiziente Dateisystem-Operationen. Ohne Abhängigkeiten.
stacks
Load stack-specific knowledge (conventions, exact lint/test/build commands, common failure patterns) onto the current role agent for the project's detected tech stack(s) — Next.js, React Native, Spring Boot, FastAPI, Django, Rust, etc. Use at the start of any task in an unfamiliar or newly-onboarded repo, or whenever…