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 YoungLeadersDotTech/young-leaders-tech-marketplace --skill diy-continuegit clone --depth 1 https://github.com/YoungLeadersDotTech/young-leaders-tech-marketplaceWrote 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/youngleadersdottech/young-leaders-tech-marketplace/diy-continue)<a href="https://agentmods.dev/skills/youngleadersdottech/young-leaders-tech-marketplace/diy-continue"><img src="https://agentmods.dev/badge/skills/youngleadersdottech/young-leaders-tech-marketplace/diy-continue/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/youngleadersdottech/young-leaders-tech-marketplace/diy-continue"><img src="https://agentmods.dev/badge/skills/youngleadersdottech/young-leaders-tech-marketplace/diy-continue.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 | $0.00055 | $0.03931 |
| Opus 5.5 | $0.00022 | $0.01572 |
| Sonnet 5.5 | $0.00011 | $0.00786 |
| Haiku 4.5 | $0.00006 | $0.00393 |
Grade A, and why
diy-continue 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 1mo 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DIY Build Companion
A single companion for planning and running DIY builds. It follows an assembly-line workflow with energy-aware work blocks and enforced breaks, and keeps project state in the build repo so every session starts from the real current state. This replaces the older five-skill suite (diy-start, diy-resume, diy-progress, diy-break, diy-safety-check) with one skill and five modes.
Before you start. If you previously installed the older five skills (diy-start, diy-resume, diy-progress, diy-break, diy-safety-check), remove them so a request does not trigger both the old and new behaviour.
The one rule
The single source of truth is the project folder in the build repo. Read it from disk before doing anything, and write changes back to disk in the same turn you make them. Do not cache state in your head across turns, and do not treat anything said in conversation as recorded until it is written to the file.
Sync before you read, commit after you write. The repo is the shared surface, so a session
that starts from a stale checkout will confidently work from old state. At the start of a session
run git pull (or tell the user to, if you cannot run commands), and after a state change commit
the updated files so the next session sees the truth. Never claim a write that did not happen
- if you have no ability to write files in this session, say so plainly and hand the user the updated file as a fenced Markdown block with the exact path to save it to. Silent false-writes are worse than an honest handback.
Project layout
All builds live under projects/ in the build repo, split by status. One folder per project,
slug-named:
projects/
active/
<project-slug>/
overview.md project name, target users, status, phase, key dimensions
state.md the living "where am I" file (see schema below)
progress-log.md append-only dated log of work blocks
safety.md safety gate record: each gate, status, findings, date
design.md (optional) current dimensions and the vertical stack
cutting-plan.md (optional) per-build planning docs
materials.md (optional)
completed/
<project-slug>/ same shape, moved here when the build is done
What ships with it
3 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.
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.
- 1mo ago Changed · +7 lines 58fc8830e1ae
- 1mo ago Changed · +9 lines e5774ee2fc01
- 1mo ago First seen · 264 lines · 55 tokens per session scan A 3ee02f50307a
diy-continue is a skill published in the GitHub repository YoungLeadersDotTech/young-leaders-tech-marketplace (10 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 3,931 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.