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 CiselyAI/agency-skills --skill cisely-agency-modelgit clone --depth 1 https://github.com/CiselyAI/agency-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/ciselyai/agency-skills/cisely-agency-model)<a href="https://agentmods.dev/skills/ciselyai/agency-skills/cisely-agency-model"><img src="https://agentmods.dev/badge/skills/ciselyai/agency-skills/cisely-agency-model/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/ciselyai/agency-skills/cisely-agency-model"><img src="https://agentmods.dev/badge/skills/ciselyai/agency-skills/cisely-agency-model.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 | $0.00133 | $0.01779 |
| Opus 5 | $0.00067 | $0.00890 |
| Sonnet 5 | $0.00027 | $0.00356 |
| Haiku 4.5 | $0.00013 | $0.00178 |
Grade A, and why
cisely-agency-model 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 10d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modeling a company in Cisely
You help the user turn their business into a navigable agency graph in Cisely, using the Cisely
MCP (tools prefixed mcp__cisely__* such as CreatePersona, SituateStakeholder,
LinkExpectationProxiesForGoal). This skill is the worldview, the discipline, and the playbook.
The worldview in one breath
A business is an exchange of value between agents. You cannot control what your stakeholders expect of you — you can only choose whom to serve and design how you meet them. Cisely makes that explicit as two sides joined by belief:
- Demand (what is wanted): a Persona (invariant WHO) holds a Goal (a latent emotional deliverable). A persona seen through an Operating Context (a lens) becomes a Stakeholder, which holds Expectations (the only directly-measurable atoms of demand). An expectation proxies for a goal.
- Response (what the business does): a Mission (the WHY) is pursued by Strategy (the HOW), which is executed by Initiatives (the WHAT). Metrics measure strategies, initiatives, and — crucially — expectations.
- Keystone: Belief. Goals and strategies both root in beliefs. When a stakeholder's goal and the business's strategy root in the same belief, that is alignment — the thing that makes a business feel inevitable.
Full primer: references/agency-model.md. Read it before a first
session so you can converse fluently about the model.
Before you start
- Check the MCP is connected. Confirm
mcp__cisely__*tools are available. If not, tell the user to run/mcp, select cisely, and complete the OAuth sign-in (orclaude mcp add --transport http cisely https://app.cisely.dev/mcp). Don't fabricate results. - Read what's already there before adding. Call the
List*tools (ListPersonas,ListStrategies,GetMission, …) so you build on the existing model instead of duplicating it. Modeling is discovery, continuous and never finished — expect to revise.
What ships with it
4 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.
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.
- 10d ago First seen · 115 lines · 133 tokens per session scan A eccc6b4790f8
cisely-agency-model is a skill published in the GitHub repository CiselyAI/agency-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 133 tokens to every session and 1,779 once invoked, about $0.0007 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
strategic-frameworks
This skill should be used when the user asks about "7 Powers", "Porter's Five Forces", "Blue Ocean", "JTBD", "Wardley Mapping", "TAM SAM SOM", "Kano Model", "RICE scoring", "ICE scoring", "strategic analysis", "competitive strategy", "market sizing", "feature evaluation frameworks", "what framework should I use"…
ceo-mindset
This skill should be used when the user asks for "CEO review", "executive evaluation", "strategic decision making", "feature go/no-go", "build vs not build decision", "assertive feedback", "should we build this", "tear this apart", "give me tough feedback", "play devil's advocate", "is this worth building", or needs…
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
google-ads-audit
Google Ads account audit and business context setup. Use for account-health audits and business-context setup. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should I fix in my ads", or when the user is new to NotFair and hasn't run…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
alive:system-upgrade
Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.