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.
git 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/review)<a href="https://agentmods.dev/commands/ciselyai/agency-skills/review"><img src="https://agentmods.dev/badge/commands/ciselyai/agency-skills/review.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 5.1 | $0.00031 | $0.00606 |
| Opus 5 | $0.00015 | $0.00303 |
| Sonnet 5 | $0.00006 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
review 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 8d 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
Run a health review of the company's Cisely model. Read-only — do not create or change anything.
Follow the cisely-agency-model skill's worldview. Optional focus: $ARGUMENTS.
-
Confirm the MCP is connected (
mcp__cisely__*); if not, tell the user to run/mcp→ cisely. -
Read the whole graph (or the focus area):
GetMission,ListBeliefs,ListPersonas,ListOperatingContexts,ListStakeholders,ListGoals,ListExpectations,ListStrategies,ListInitiatives,ListMetrics. UseGet*to inspect declarations and follow edges where needed. -
Report on these dimensions (be specific — name the nodes, link them with their
https://app.cisely.dev/concise/...URLs):- Lifecycle hygiene — what's still a DRAFT (hollow, not yet activated), and what content gate is blocking it (e.g. a goal with no statement, a strategy missing its core choices, an initiative with no falsifiable hypothesis).
- Demand coverage — personas with no goals; goals not rooted in any belief; stakeholders with no expectations; expectations not proxying any goal (orphan proxies); latent/emerging expectations that are candidates for sharpening.
- Response coverage — does a mission exist and is it active? strategies not rooted in a belief; strategies with no initiatives; initiatives with no metric; metrics measuring nothing.
- The loop — expectations with no metric measuring them (the demand↔response loop is open there); metrics with no recent observations.
- Alignment (the headline) — for each belief, list the goals and the strategies that root in it. Call out the wins: a belief that both a stakeholder goal and a business strategy root in is alignment realized. Call out the risks: strategies rooted in beliefs no stakeholder shares, or central stakeholder goals rooting in beliefs no strategy responds to.
-
End with a short, prioritized list of the highest-leverage next moves (e.g. "activate these 3 draft personas", "this goal has no strategy serving it", "no expectation is measured — close the loop on
<expectation>"). Frame declined/absent items as decisions to confirm, not just gaps.
Offer to act on any item via /cisely:model, or to chart a /cisely:canvas for a chosen persona.
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.
- 8d ago First seen · 38 lines · 31 tokens per session scan A 017749d2d56b
review is a command published in the GitHub repository CiselyAI/agency-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 606 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.
learn
Force claude-smart to extract learnings from this session now.
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
A command for safely shortening Markdown or text files into the genshijin style.
check-dev
Type-check a Z specification with fuzz.