tech-leadership

tech-leadership is a skill for Claude Code, Codex from oghie/skillsets. It costs 76 tokens per session (2,989 once invoked), scanned A, original, MIT.

A guide for technology leadership across strategy, engineering delivery, cybersecurity, people, budgets, governance, and risk. It treats technology leadership as a system of priorities, decisions, responsibilities, and measurable results.

In plain words
What is it for?
Use it for technology strategy, roadmaps, budgets, organizational design, hiring, delivery recovery, cybersecurity planning, audits, vendor decisions, and executive reporting.
Why use it?
It helps turn broad leadership problems into explicit choices about goals, capacity, trade-offs, ownership, and progress. It also provides a way to structure plans and reports.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the skillsets plugin — 9 skills, 4 commands, 1 hook, 4 MCP servers shipped together

Good fit Use it for technology strategy, roadmaps, budgets, organizational design, hiring, delivery recovery, cybersecurity planning, audits, vendor decisions, and executive reporting.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oghie/skillsets/tech-leadership
Install

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.

Any agent
npx skills add oghie/skillsets --skill tech-leadership
Clone the repo
git clone --depth 1 https://github.com/oghie/skillsets

Made for: Claude Code, Codex.

Or install skillsets, the plugin that ships this one along with the rest of its 9 skills, 4 commands, 1 hook, 4 MCP servers.

Wrote 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.

agentmods badge for tech-leadership

README.md
[![agentmods](https://agentmods.dev/badge/skills/oghie/skillsets/tech-leadership/github.svg)](https://agentmods.dev/skills/oghie/skillsets/tech-leadership)
Your own site
<a href="https://agentmods.dev/skills/oghie/skillsets/tech-leadership"><img src="https://agentmods.dev/badge/skills/oghie/skillsets/tech-leadership/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.

agentmods 80×15 button for tech-leadership

Your own site · 80×15
<a href="https://agentmods.dev/skills/oghie/skillsets/tech-leadership"><img src="https://agentmods.dev/badge/skills/oghie/skillsets/tech-leadership.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.02989
Opus 5 $0.00038 $0.01494
Sonnet 5 $0.00015 $0.00598
Haiku 4.5 $0.00008 $0.00299

Measured 11d ago against content hash 48defb2d0927, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

tech-leadership 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 11d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/generate_leadership_artifact.py, scripts/tech_leadership_static_audit.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/tech-leadership/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Leadership

Core Rule

Treat technology leadership as an operating system, not a motivational role. Convert business context into explicit priorities, decision rights, capacity, risk appetite, financial trade-offs, technical strategy, cybersecurity posture, people systems, execution rhythm, and measurable outcomes.

First Pass

  1. Classify the request: daily operating review, strategy, roadmap, portfolio, cybersecurity strategy, SME/COE, functional/technical requirements, framework selection, audit/compliance, board/shareholder report, delivery recovery, incident management, organization design, hiring/retention, appraisal, budget, vendor/partner strategy, R&D, AI/data transformation, culture, political risk, or cross-functional advisory.
  2. Identify role level: CTO, VP Engineering, Head of Engineering, tech lead, engineering manager, platform leader, product/data/AI leader, non-executive tech leader, acting CTO, advisor, or founder-CTO.
  3. Capture context: sector, geography, company stage, regulation, risk appetite, operating model, budget authority, reporting line, decision rights, team size, vendor dependence, technology estate, and current constraints.
  4. Separate Fact, Inference, Assumption, and Question. Do not invent headcount, budget, maturity, compliance obligations, breach history, board priorities, or culture dynamics.
  5. Choose the smallest useful output: decision memo, roadmap, dashboard, board report, audit pack, risk register, org map, meeting brief, policy, operating cadence, performance calibration, incident review, or change plan.
  6. Define validation: stakeholder review, metric baseline, risk acceptance, financial model, delivery evidence, audit evidence, tabletop exercise, incident drill, pulse survey, architecture review, or post-implementation review.

Required Reads By Task

  • Operating cadence, daily/weekly/monthly leadership work, decision rights, or CTO operating model: references/leadership-operating-system.md.
  • Strategy, short/mid/long-term planning, roadmap, portfolio trade-offs, technology bets, technical debt, scalability, resilience, sustaining engineering, roadmap uncertainty, or over-engineering: references/strategy-roadmap-portfolio.md.
  • Senior technology leadership role design, CTO vs VP Engineering, executive peer trust, senior leadership tasks, technical True North, role modeling, or business/technology executive alignment: references/senior-technology-leadership.md.
  • KPI, KRA, OKR, CSF, scorecard, dashboard, performance reporting, root cause analysis, balanced scorecard, benchmarking, performance management system, or metric design: references/metrics-kpi-dashboard.md.
  • Executive and managerial quantification, CTO metrics, technology value metrics, manager-system metrics, board metric synthesis, team diagnostic metrics, metric harm, or modern technology leadership blind spots: references/executive-managerial-quantification.md.
  • Hiring, developing, retaining, mentoring, delegation, 1:1s, skip-level meetings, managing managers, manager accountability, calibration, appraisal, 360 feedback, incentives, team allocation, or succession: references/people-org-talent-appraisal.md.
  • Enterprise risk, audit readiness, compliance, policy, controls, regulatory exposure, or governance: references/governance-risk-compliance-audit.md.
  • SME, Subject Matter Expert, Center of Excellence, COE, community of practice, expert review, capability enablement, platform/service COE, governance COE, or reusable expert capability: references/sme-coe-operating-model.md.
  • Functional requirements, technical requirements, product/engineering specs, non-functional requirements, acceptance criteria, traceability, launch readiness, migration requirements, or requirement review: references/requirements-engineering-for-tech-leads.md.
  • Selecting or critiquing ITSM, ITIL, COBIT, TOGAF, ISO/IEC/IEEE, PCI DSS, PMBOK, CMMI, AICPA/SOC 2, CNCF, Gartner Magic Quadrant, HIPAA, GDPR, PDP, SAFe, Lean Six Sigma, DORA, MTTR, or deciding no framework: references/framework-selection-and-critical-prompts.md.
  • Socio-technical risk, reliability management, hidden risk, near misses, barriers, redundancies, recoveries, just culture, burnout risk, human reliability, system reliability, organizational reliability, or predictive reliability: references/risk-reliability-leadership.md.
  • Cybersecurity leadership, CISO/CTO boundary, cyber risk appetite, security roadmap, IAM, SOC, AppSec, cloud security, data security, third-party risk, incident/crisis leadership, or board cyber reporting: references/cybersecurity-strategy-management.md.
  • Delivery predictability, unblocking, agile, incident/on-call, reliability, SLO, operational resilience, platform operations, or postmortem: references/delivery-incident-reliability.md.
  • Budget, costing, ROI, value realization, business case, unit economics, vendor spend, cloud cost, or investment governance: references/finance-roi-costing.md.
  • AI leadership, AI agents, agent autonomy, AI observability, AI security, AI ROI, data/product leadership, data value, R&D, technology research, innovation, experiments, hypotheses, evaluation, and adoption governance: references/ai-data-rd-innovation.md.
  • Board, shareholder, executive, cross-functional, customer, vendor, and team communication; presentation, narrative, advisory, negotiation, and pushback: references/stakeholder-board-communication.md.
  • Engineering culture, structure, career ladders, cross-functional pods, process-as-risk-management, code review, architecture review, learning reviews, Conway's Law, psychological safety, and scale-stage structure: references/engineering-culture-structure-process.md.
  • Culture, incentives, organizational politics, power mapping, psychological safety, cross-cultural leadership, and office politics defense: references/culture-politics-cross-cultural.md.
  • Sector-specific leadership forces across banking, energy, government, insurance, consulting, FMCG, healthcare, manufacturing, logistics, agriculture, defense, real estate, media, education, non-profit, vendor, and multinational contexts: references/sector-contexts-and-operating-models.md.
  • Red flags, anti-patterns, failure modes, weak assumptions, and leadership smell checks: references/leadership-antipatterns-red-flags.md.

Read the full file on GitHub · 121 lines

Files

What ships with it

60 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.

Changes

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.

  1. 11d ago First seen · 121 lines · 76 tokens per session scan A 48defb2d0927

Subscribe to this mod's changes

tech-leadership is a skill published in the GitHub repository oghie/skillsets (9 stars, last pushed 1mo ago), licensed MIT. It adds 76 tokens to every session and 2,989 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.

Related

Other skills, from other repositories

coauthor-brief

Generate a co-author / collaborator handoff brief for a multi-author, multi-machine project — summarizing what changed since the last brief (git delta), the current state of each artifact (manuscript, analysis, slides), open questions, how to reproduce locally, and any restricted-data access steps. Use when user says…

pedrohcgs/claude-code-my-workflow · 146 tokens

triage-inbox

Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…

pedrohcgs/claude-code-my-workflow · 132 tokens

project-retrospective

Generates LESSONS.md files capturing institutional knowledge and failures. Use when closing out projects or investigations.

jamditis/claude-skills-journalism · 26 tokens

editorial-workflow

Manages newsroom editorial workflows. Use when tracking assignments, managing deadlines, or coordinating editorial calendars.

jamditis/claude-skills-journalism · 24 tokens

light-memory-pm

A project memory and management system that stores status, decisions, versions, agreed terms, and handoff notes in each project’s .light/ folder.

Light0305/Light-skills · 368 tokens

before-you-build

Pre-build product and feature risk review for founders, product managers, and AI-assisted builders. Use this skill when the user is about to build a landing page, MVP, SaaS product, internal tool, agent workflow, or major feature and needs to check demand, positioning, monetization, retention, trust, distribution, and…

FridrichMethod/awesome-skills · 75 tokens