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 Kimyongari/harness-factory --skill quick-tasksgit clone --depth 1 https://github.com/Kimyongari/harness-factoryWrote 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/kimyongari/harness-factory/quick-tasks)<a href="https://agentmods.dev/skills/kimyongari/harness-factory/quick-tasks"><img src="https://agentmods.dev/badge/skills/kimyongari/harness-factory/quick-tasks/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/kimyongari/harness-factory/quick-tasks"><img src="https://agentmods.dev/badge/skills/kimyongari/harness-factory/quick-tasks.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 | $0.00073 | $0.00470 |
| Opus 5 | $0.00036 | $0.00235 |
| Sonnet 5 | $0.00015 | $0.00094 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
quick-tasks 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 10d 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.
What it actually says
Daily / lightweight tasks (token saving)
Purpose: don't spend a big process on a small request. Safety rules (AGENT.md, hooks) stay in force; only the process gets lighter.
Qualification — may this run in light mode?
Proceed in light mode only if ALL hold:
- You already know the target file, or one search pins it down
- There is no design decision (you are fixing, not choosing behavior)
- The diff is roughly under 20 lines
If any fails, switch to the development skill (Read → Think → Plan → Edit → Verify).
Announce the switch — one line like "scope grew, switching to the normal process".
Light-mode rules
- Minimal reading: open only the target file (and what it directly references). No pre-emptive browsing.
- Skip the plan doc: don't create or update
PLAN.md. The moment steps appear, this isn't light mode. - No drive-by changes: don't do refactors you happen to notice. One line in
.docs/plans/tech-debt.md, move on. - Report in ≤3 sentences: what changed, how you verified. No background essays or option lists.
- Never skip verification: passing
.scripts/verify.shdefines "done" in light mode too. (The hook enforces it anyway — don't try to route around it.)
Examples
| Request | Handling |
|---|---|
| "bump the timeout to 5s" | locate the constant → edit → verify → one-line report |
| "what's this error?" | read only the file in the stack, explain the cause (don't fix until asked) |
| "fix the README typo" | edit → verify → done |
| "change the login flow" | not light — announce switch to development and proceed |
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.
- 10d ago First seen · 35 lines · 73 tokens per session scan A f32c8628f737
quick-tasks is a skill published in the GitHub repository Kimyongari/harness-factory (5 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 470 once invoked, about $0.0004 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
workspace-brief
Build a concise, evidence-backed briefing from workspace status and recent commits.
google-workspace
Fetch and query data from Google Workspace using the gws CLI — Gmail, Calendar, Docs, Sheets, Slides, and Drive. Use this skill whenever the user mentions email, inbox, messages, calendar, meetings, schedule, agenda, Google Docs, spreadsheets, presentations, or Drive files. Trigger on phrases like "check my email"…
email-meeting-summary
Use when the user wants to summarize a Google Meet meeting and send the summary by email. Reviews a Google Meet transcript for a specific meeting topic, then composes a Gmail draft summarizing decisions and action items for that topic. Prompts for meeting selection if not specified, and for topic selection before…
gmail-draft
Use this skill to compose a Gmail draft from text content in the conversation. Accepts a body, recipient list, and subject — either from the user or from context — and creates a draft in the user's Gmail Drafts folder via gws.
anti-slop-design
Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…
3d-web-experiences
Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…