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 cpliakas/claude-code-engineering-leaders --skill onboardgit clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leadersWrote 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/cpliakas/claude-code-engineering-leaders/onboard)<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/onboard"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/onboard.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.04957 |
| Opus 5 | $0.00036 | $0.02478 |
| Sonnet 5 | $0.00014 | $0.00991 |
| Haiku 4.5 | $0.00007 | $0.00496 |
Grade A, and why
onboard 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 6d 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 — 558 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard
Gather shared project context for all engineering-leaders agents and discover specialist plugins for the Tech Lead to consult.
This skill runs a guided interview. It asks one question at a time and writes the results to a shared memory file that every agent in this plugin reads.
Output Location
Shared context is written to:
.claude/agent-memory/engineering-leaders/PROJECT.md
Specialist routing entries are written to:
.claude/agent-memory/engineering-leaders-tech-lead/MEMORY.md
Per-project agent model overrides (written only when the user selects a non-default trade-off during the Model Selection step) are written to:
.claude/agents/<agent-name>.md
Process
Step 1: Check for Existing Context
Read .claude/agent-memory/engineering-leaders/PROJECT.md if it exists.
If it does not exist, proceed directly to Step 2. Track: context_written = false.
If it exists, show the user a brief summary of what is recorded (project name, tech stack, current phase) and ask:
"Shared project context already exists. Would you like to:
(a) Update specific sections — I'll ask which sections to replace and re-run only those questions. All other sections are preserved unchanged. (b) Start fresh — I'll run the full interview and replace the entire file when complete. If you abandon the interview before finishing, the original file is left unchanged. (c) Skip to specialist discovery — skip the project context interview and go straight to updating the Tech Lead specialist registry."
If the user chooses (a):
Show the list of sections in the existing file (Project Overview, Tech Stack, Team, Key Constraints, Specialists, Model Selection) and ask: "Which sections would you like to update?" Re-ask only the questions that correspond to the sections they name (Q1, Q2, and Q6 for Project Overview; Q3 for Tech Stack; Q4 and Q5 for Team; Q7 for Key Constraints; Step 4 for Specialists; Step 5 for Model Selection), then merge the new answers into the existing file by replacing only those sections. Sections not selected are preserved verbatim from the original. Any content in the file that does not correspond to a template section (e.g., manually added sections) must also be preserved verbatim — do not discard unrecognized content.
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.
- 6d ago First seen · 558 lines · 71 tokens per session scan A ab1aa6d97b84
onboard is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 15d ago), licensed MIT. It adds 71 tokens to every session and 4,957 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…