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 fatihguner/foreman --skill belbin-team-rolesgit clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/belbin-team-roles)<a href="https://agentmods.dev/skills/fatihguner/foreman/belbin-team-roles"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/belbin-team-roles/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/fatihguner/foreman/belbin-team-roles"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/belbin-team-roles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.03207 |
| Opus 5 | $0.00044 | $0.01604 |
| Sonnet 5 | $0.00017 | $0.00641 |
| Haiku 4.5 | $0.00009 | $0.00321 |
Grade A, and why
belbin-team-roles 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.
Belbin Team Roles
In 2004, the United States assembled a basketball team for the Athens Olympics that included LeBron James, Tim Duncan, Allen Iverson, and Carmelo Anthony -- arguable the most talented collection of individual players ever put on a court together. They lost three games and settled for bronze. Eight years later, a Spanish national team with no single player approaching that caliber won silver and pushed the Americans to the limit. The pattern repeats across every team sport, every corporate acquisition of "star" talent, and every startup that hires exclusively from elite pedigrees: assembling the best individuals does not produce the best team.
Meredith Belbin spent nine years at Henley Management College studying why some teams of brilliant people underperformed while other teams of average individuals consistently excelled. His research, published in Management Teams: Why They Succeed or Fail (1981), produced a taxonomy of nine team roles -- behavioral patterns that individuals adopt in group settings -- and a principle that has survived four decades of scrutiny: balanced teams outperform unbalanced teams, regardless of the individual talent level within them.
The Framework
Belbin's nine roles cluster into three categories: Thinking roles, Action roles, and People roles. Each role contributes a specific strength and carries an "allowable weakness" -- a predictable downside that is the shadow of the strength. Effective teams do not eliminate weaknesses; they ensure that every weakness is compensated by another role's strength.
Thinking Roles
Plant (PL)
- Contribution: Creative, imaginative, unorthodox. Generates novel ideas and solves difficult problems.
- Allowable weakness: Ignores practical details. May be too absorbed in ideas to communicate effectively.
- Startup translation: The visionary co-founder who sees possibilities no one else does -- and forgets to check whether the technology exists to build them.
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 Changed · +199 lines · +87 tokens per session d1d4427a2a2c
- 12d ago First seen · 1 lines · 0 tokens per session scan A 48b9aecd5eaf
belbin-team-roles is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 3,207 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 2026-08-30.
Other skills, from other repositories
design-team-norms
Use when a team is forming, after a significant membership change, or when a recurring dysfunction suggests the team lacks shared agreements on how to work together — to co-create explicit norms covering communication, decision-making, conflict, and accountability.
team-lead-collaboration
Markdown collaboration Lead. Use only when the user explicitly selects $team-lead-collaboration to organize lightweight project collaboration.
team-member-collaboration
Markdown collaboration Member. Use only when the user explicitly selects $team-member-collaboration for assigned project work.
manage-taskboard
Manage Codex Taskboard / e-taskboard work with taskctl. Use for taskboard issue IDs, status sync, comments, or taskctl cloud setup—not for unrelated product docs.
decision-map
Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…
fly
Fly one thought to its destination across concurrent agents, on whatever the project and harness already have. Lands only when the user has accounted for every detail, never on an agent's say-so.