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 modest-curator478/claude-skills --skill small-team-managementgit clone --depth 1 https://github.com/modest-curator478/claude-skillsWrote 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/modest-curator478/claude-skills/small-team-management)<a href="https://agentmods.dev/skills/modest-curator478/claude-skills/small-team-management"><img src="https://agentmods.dev/badge/skills/modest-curator478/claude-skills/small-team-management/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/modest-curator478/claude-skills/small-team-management"><img src="https://agentmods.dev/badge/skills/modest-curator478/claude-skills/small-team-management.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 | $0.00231 | $0.03913 |
| Opus 5 | $0.00115 | $0.01956 |
| Sonnet 5 | $0.00046 | $0.00783 |
| Haiku 4.5 | $0.00023 | $0.00391 |
Grade A, and why
small-team-management 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.
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.
This is a copy
100% identical to small-team-management — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 425 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Small Team Management: People Skills for the Practitioner Who Came Up Through the Function
This skill addresses the people management challenges of a Director who built their career in demand gen, RevOps, or marketing operations and now manages a small team of two to six people. Most Directors in this position learned their function deeply but learned management on the job. The result is a leader who is technically excellent and managerially uneven, not because they are not capable, but because no one taught them the specific skills that make a small team work.
The problems this skill addresses are different from HR problems. HR manages processes, documentation, and legal compliance. This skill manages the actual human dynamics of a small team: how to have the feedback conversation that changes behavior, how to identify the person who is quietly underperforming before it becomes a crisis, how to run a one-on-one that is worth the time on both sides, and how to make the call on letting someone go without doing it wrong.
HOW TO SET UP THIS SKILL
Provide:
- Team size and structure: how many direct reports, what their roles are
- The specific situation: a performance issue, a feedback conversation you are preparing for, a one-on-one that is not working, or a team dynamic problem
- How long the person has been on the team and in the role
- What you have already tried
- Whether HR has been involved or needs to be
The One-on-One That Actually Works
Most one-on-ones in marketing and RevOps functions are status updates. The manager asks what is happening, the direct report gives a summary of their week, and nothing changes as a result of the conversation. That is a waste of thirty minutes for both people.
A one-on-one that functions well accomplishes three things the status update does not: it surfaces problems before they become visible to leadership, it gives the direct report a space to raise things they would not raise in a team meeting, and it builds the working relationship that makes feedback land when it needs to.
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.
- 11d ago First seen · 425 lines · 231 tokens per session scan A 015001899055
small-team-management is a skill published in the GitHub repository modest-curator478/claude-skills (4 stars, last pushed yesterday), licensed MIT. It adds 231 tokens to every session and 3,913 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to small-team-management, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
atlassian-mcp
Use when querying Jira issues, searching Confluence pages, creating tickets, updating documentation, or integrating Atlassian tools via MCP protocol.
github-issue-fetcher
This skill should be used when users need to fetch GitHub issues from the current repository, including getting the next issue to work on, retrieving specific issue fields (body, number, title, labels, etc.), or querying issues with custom sorting and filtering. Triggers on requests like "get the next GitHub issue"…
loki-mode
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention.…
TEMPLATE
../../../agents/personas/TEMPLATE.md.
task
AI DevKit · Track dev-lifecycle / structured-debug progress on a durable task with the ai-devkit task CLI. Use to record phase, progress, next step, blockers, and validation evidence.
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.