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 agentmods add commands/ciselyai/agency-skills/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/commands/ciselyai/agency-skills/model)<a href="https://agentmods.dev/commands/ciselyai/agency-skills/model"><img src="https://agentmods.dev/badge/commands/ciselyai/agency-skills/model.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00701 |
| Opus 5 | $0.00016 | $0.00351 |
| Sonnet 5 | $0.00007 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
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 3d 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.
What it actually says
Begin a Cisely modeling session. Follow the cisely-agency-model skill throughout — its worldview,
build order, and the high-rigor operating principles are binding here.
User input (optional focus or source to ingest): $ARGUMENTS
Work through these steps:
-
Verify the connection. Confirm the Cisely MCP tools (
mcp__cisely__*) are available. If they are not, stop and tell the user to run/mcp→ select cisely → complete the OAuth sign-in (orclaude mcp add --transport http cisely https://app.cisely.dev/mcp). Do not pretend to write data. -
Take stock of what exists. Before proposing anything, read the current model:
GetMission,ListBeliefs,ListPersonas,ListOperatingContexts,ListStakeholders,ListGoals,ListExpectations,ListStrategies,ListInitiatives,ListMetrics. Give the user a short, honest summary of where the model stands today and the biggest gaps (e.g. "no mission yet", "personas exist but none have goals", "strategies don't root in any belief"). -
Choose a mode (unless
$ARGUMENTSalready implies one — a file/URL ⇒ ingest; a topic ⇒ focus):- Interview — elicit the model Socratically (see the skill's playbook reference). Start where it pays most: usually the mission, or the single most important persona and what it really wants.
- Ingest — read the material the user pointed at, extract candidate personas / goals / contexts / expectations / strategy, and present the proposed graph for approval before writing.
-
Model, with discipline. Respect the build order (mission → beliefs → demand side → response side). For each concept: propose it, confirm with the user, then
Create → Revise → Activate. Wire the edges (born-linked ones happen automatically; authorROOTED_IN,PROXIES_FOR, andMEASURESyourself). Actively look for goals and strategies that should root in the same belief — that convergence is the alignment payoff. -
Show the work. After each change, give the user the View in Cisely deep link the tool returns, and periodically point at the Agency Board (
https://app.cisely.dev/concise/agency) and Purpose Board (https://app.cisely.dev/concise/purpose). -
Close the loop. When a coherent slice exists, offer to run
/cisely:review(coverage, gaps, alignment) or/cisely:canvas(Jobs-to-be-Done + Value Proposition Canvas).
Keep it conversational and incremental. Don't bulk-create without the user seeing the shape, and treat every "we don't serve that" as a deliberate decision worth recording, not an omission.
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.
- 3d ago First seen · 44 lines · 33 tokens per session scan A eaeda6f25fa0
model is a command published in the GitHub repository CiselyAI/agency-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 701 once invoked, about $0.0002 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 commands, from other repositories
ceo-review
Run a CEO-level strategic review of a feature before development.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.