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 marcos-sponton/frameworks-as-skills --skill scaling-peoplegit clone --depth 1 https://github.com/marcos-sponton/frameworks-as-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/marcos-sponton/frameworks-as-skills/scaling-people)<a href="https://agentmods.dev/skills/marcos-sponton/frameworks-as-skills/scaling-people"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/scaling-people/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/marcos-sponton/frameworks-as-skills/scaling-people"><img src="https://agentmods.dev/badge/skills/marcos-sponton/frameworks-as-skills/scaling-people.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 | $0.00456 | $0.03817 |
| Opus 5 | $0.00228 | $0.01909 |
| Sonnet 5 | $0.00091 | $0.00763 |
| Haiku 4.5 | $0.00046 | $0.00382 |
Grade A, and why
scaling-people 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 12d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaling People
Claire Hughes Johnson's operating system for building companies at scale. Distilled from Scaling People: Tactics for Management and Company Building (Stripe Press, 2023) — the book that captured what Claire actually did as COO of Stripe from 2014 to 2021, scaling the company from fewer than 200 employees to over 7,000. Before Stripe, ~10 years at Google leading business teams across Gmail, AdWords, Google Apps, and the self-driving car project.
Distinct from other management books in the repo because it is explicitly a reference book with over 100 pages of worksheets, templates, and example documents. Claire herself says the book is "designed so you can go into the table of contents and not expect to read it cover to cover." This skill mirrors that: it is a template router as much as a method explainer. When the user is stuck, the answer is usually "here is the template Claire would hand you, plus the failure mode to watch for."
When this skill activates
Use this skill when the user is:
- Scaling an org past the "everyone in one room" stage (roughly 20–1000 people, though the tools generalize).
- Writing or refreshing their founding documents — mission, long-term goals, values, team charters.
- Drafting a personal operating manual ("Working with X") for themselves or asking a new hire / direct report to.
- Designing a hiring loop — job description, interview rubric, scorecard, interview committee, bar-raiser role.
- Doing reference calls on a senior hire — the ranking question, the coaching question, priming the referee.
- Running or redesigning 1:1s, performance reviews, and comp calibration.
- Diagnosing why a team is stuck — the operating system as the diagnostic lens, not the individuals.
- Thinking through a re-org or team restructure.
- Planning an offsite — Claire has a public toolkit that maps to this skill.
- Giving hard feedback to a report — hypothesis-based coaching, "say the thing you think you cannot say."
- Managing a low performer through Claire's four-phase escalation.
- Building the operating cadence (charters annually, OKRs quarterly, reviews per-team) of a hypergrowth company.
- Executive hiring specifically — the "did they build followership in 3–6 months?" test, the "tell me about your current team and why you chose that structure" question.
What ships with it
12 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.
- evals/evals.json 15 KB
- examples/.gitkeep 0 B
- README.md 8.9 KB
- references/applications.md 15 KB
- references/author-live-sources.md 10 KB
- references/examples.md 11 KB
- references/heuristics.md 18 KB
- references/method.md 27 KB
- references/post-book.md 11 KB
- references/prompts.md 15 KB
- references/sources.md 8.7 KB
- references/voice-and-tone.md 16 KB
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.
- 12d ago First seen · 111 lines · 456 tokens per session scan A 2333e59470b9
scaling-people is a skill published in the GitHub repository marcos-sponton/frameworks-as-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 456 tokens to every session and 3,817 once invoked, about $0.0023 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
cc-skill-project-guidelines-example
Project Guidelines Skill (Example).
grace-status
Show GRACE 4 project health across .grace context, graph, verification, active changes, scopes, and migration boundaries.
belbin-team-roles
Analyzes team composition using Belbin's nine team roles across Thinking, Action, and People categories. Maps team members to roles such as Plant, Shaper, Coordinator, Implementer, and others to identify gaps, overlaps, and imbalances. Use when hiring to fill role gaps, diagnosing recurring team conflicts, auditing…
doblin-ten-types
Maps and designs innovation strategy using Doblin's Ten Types of Innovation across Configuration (Profit Model, Network, Structure, Process), Offering (Product Performance, Product System), and Experience (Service, Channel, Brand, Customer Engagement). Use when auditing current innovation profile, identifying…
giving-feedback
Structures effective feedback conversations using the Situation-Behaviour-Impact (SBI) model from the Center for Creative Leadership. Separates observable behavior from interpretation, anchors feedback in specific situations, and articulates concrete impact. Use when preparing difficult performance conversations…
hackman-enabling-conditions
Diagnoses and designs team effectiveness using Hackman's six enabling conditions: a real team, compelling direction, right people, sound structure, supportive context, and expert coaching. Shifts focus from blaming team members to establishing the structural and environmental conditions that make high performance…