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/canvas)<a href="https://agentmods.dev/commands/ciselyai/agency-skills/canvas"><img src="https://agentmods.dev/badge/commands/ciselyai/agency-skills/canvas.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 | $0.00024 | $0.00623 |
| Opus 5 | $0.00012 | $0.00311 |
| Sonnet 5 | $0.00005 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
canvas 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
Synthesize Jobs-to-be-Done and a Value Proposition Canvas for a persona/stakeholder, as a
read-only view derived from the Cisely graph. Do not author or change anything. Follow the
cisely-agency-model skill and its references/synthesis.md.
Target: $ARGUMENTS.
-
Confirm the MCP is connected (
mcp__cisely__*); if not, tell the user to run/mcp→ cisely. -
Resolve the target. If
$ARGUMENTSis empty or ambiguous,ListPersonasand ask the user which persona (and optionally which operating context / stakeholder) to chart. -
Gather the demand side —
GetPersona; its goals (ListGoals); its stakeholders (ListStakeholders) and their expectations (ListExpectations); followPROXIES_FORfrom each expectation to its goal; note each expectation's valence (PAIN/GAIN) and articulation. -
Gather the response side — the strategies serving this persona/context, their initiatives (
ListInitiatives), and the metrics measuring those expectations/initiatives (ListMetrics). -
Render Jobs-to-be-Done — one job story per defined expectation: "When
<operating context>, I want to<expectation>, so I can<goal>." Flag latent/emerging expectations as not-yet-crisp jobs (a discovery opportunity). -
Render the Value Proposition Canvas:
- Customer profile — Jobs (goals), Pains (PAIN-valence expectations), Gains (GAIN-valence).
- Value map — Products/services & pain relievers/gain creators (the initiatives), and the metrics that track them.
- Fit — for each committed expectation: is there an initiative addressing it and a metric showing it's met? Mark good fit, gaps (committed but unaddressed/unmeasured), and deliberate non-fit (expectations the strategy declined — a decision, not a hole).
-
Cite provenance. For each fragment, name the source node and give its
https://app.cisely.dev/concise/...link, so the user can click through and nothing in the view can silently disagree with the graph.
Note that this is a living view: it re-renders as the model changes. Offer /cisely:review for the
whole-model health check, or /cisely:model to fill a gap the canvas exposed.
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 · 41 lines · 24 tokens per session scan A 63d47097c38c
canvas is a command published in the GitHub repository CiselyAI/agency-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 623 once invoked, about $0.0001 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.