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 tms-tungnguyen3/daily_working --skill daily-workinggit clone --depth 1 https://github.com/tms-tungnguyen3/daily_workingWrote 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/tms-tungnguyen3/daily_working/daily-working)<a href="https://agentmods.dev/skills/tms-tungnguyen3/daily_working/daily-working"><img src="https://agentmods.dev/badge/skills/tms-tungnguyen3/daily_working/daily-working/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/tms-tungnguyen3/daily_working/daily-working"><img src="https://agentmods.dev/badge/skills/tms-tungnguyen3/daily_working/daily-working.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 | $0.00098 | $0.01557 |
| Opus 5 | $0.00049 | $0.00779 |
| Sonnet 5 | $0.00020 | $0.00311 |
| Haiku 4.5 | $0.00010 | $0.00156 |
Grade A, and why
daily-working 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 yesterday.
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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
daily-working
Purpose
Coordinate a full task-to-verified-change loop without the human relaying context by hand: fetch a task from the project's task tracker (with attachments), judge whether it's actually safe and sensible to implement as understood, implement it following the target project's own conventions, verify the result in a real running browser, and close the loop back on the tracker (PR + comment + status) once that's confirmed.
Task tracker support today: Redmine and GitHub Issues. task_tracker in .claude/daily-working.yml picks one; the pipeline itself (phases/fetch-task, phases/close, templates/tracker-write) only ever calls a small fixed contract — fetch, write_comment, set_status — defined in policies/tracker-adapter. Each tracker's actual mechanics live in their own adapters/<name>.md file. Adding a third tracker means writing one new adapter file; nothing under phases/, workflows/, or templates/ needs to change.
If a requirement turns out ambiguous, unreasonable, or too high-impact to proceed on quietly at any point, that gets escalated to a comment on the tracker (not just asked in this chat) and the pipeline pauses — see policies/safety.
This skill is a coordinator — it does not replace the target project's own test conventions. It sequences task tracker → implementation → live browser check → tracker update.
When to Use
- User gives a task/ticket ID from the project's tracker (e.g.
#4626, or a ticket key likePROJ-4626if this project's commits use one) and asks to implement it - User says "lấy task từ redmine", "làm task này", "pull the ticket and implement it"
- User asks to verify/review an already-implemented change against a ticket
- User asks to resume a ticket that was previously paused on an open question
- Any request that should end with a live UI check, not just passing tests
What ships with it
20 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.
- adapters/github.md 4.5 KB
- adapters/redmine.md 5.1 KB
- phases/assess.md 3.0 KB
- phases/close.md 2.3 KB
- phases/fetch-task.md 4.3 KB
- phases/implement.md 2.6 KB
- phases/setup.md 6.0 KB
- phases/test.md 990 B
- phases/verify.md 1.1 KB
- policies/browser.md 2.9 KB
- policies/database.md 1.9 KB
- policies/git.md 1.3 KB
- policies/safety.md 3.4 KB
- policies/tracker-adapter.md 4.0 KB
- templates/pr.md 1.6 KB
- templates/summary.md 613 B
- templates/tracker-write.md 1.9 KB
- workflows/implement.md 2.3 KB
- workflows/resume.md 2.1 KB
- workflows/review.md 1.9 KB
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.
- yesterday Changed a6574b6cc8b3
- 2d ago Changed · -255 lines · +17 tokens per session scan D → A 07719846974b
- 12d ago First seen · 335 lines · 81 tokens per session scan D 50424ea930e9
daily-working is a skill published in the GitHub repository tms-tungnguyen3/daily_working (5 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 1,557 once invoked, about $0.0005 per session on Opus 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
work
Dispatch a tracker ticket into an isolated worktree and drive it autonomously to an open pull request, then stop for review. Pass interactive to brainstorm the ticket with a human before planning it, or a sentence of editorial direction as a rider. Use when asked to work a ticket end-to-end.
batch
Dispatch a night's batch of Todo tickets — one worktree and one pull request each — and leave a morning summary. Run explicitly; never inferred.
prep
Spec a ticket before it is dispatched. Brainstorms it, decides everything it can recommend an answer for, asks a present human about the little that survives, and leaves the spec, the decisions and anything still open as one ticket comment. No worktree, no branch, no pull request, and the ticket stays where it was.
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.