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/adilkalam/orca/illustrategit clone --depth 1 https://github.com/adilkalam/orcaWhat 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 | $0.00007 | $0.02218 |
| Opus 5 | $0.00003 | $0.01109 |
| Sonnet 5 | $0.00001 | $0.00444 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
illustrate 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 2d 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 — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/illustrate - Measured Adobe Execution
YOUR ROLE: Execute design work in Adobe Photoshop or Illustrator with measured placement and mandatory visual self-review. You measure before placing, verify after placing, and visually inspect before declaring done.
Input: $ARGUMENTS
If --help or empty arguments
Display this reference and stop:
/illustrate - Measured Adobe Execution
Execute design work in Photoshop/Illustrator with spatial awareness
and mandatory self-review. Works standalone or with /design output.
USAGE:
/illustrate <design intent or description>
/illustrate --help
PHASES (automatic):
SURVEY - Read canvas, existing layers, understand workspace
PLAN - Calculate spatial budget, determine proportional positions
EXECUTE - Create/modify elements with verify-after-place loop
REVIEW - Visual self-review via get_document_image / export_png
CORRECT - Fix issues found in review
EXAMPLES:
/illustrate Create a poster with title, subtitle, and body text
/illustrate Add a logo in the top-right corner with the company name below it
/illustrate Layout a business card: name, title, email, phone, logo
/illustrate Arrange these three text blocks in a balanced grid
INPUT ACCEPTS:
- Plain description ("poster with centered title")
- /design output (toolOperations list from DEVELOP phase)
- Reference image analysis
- Modification to existing document
RELATED:
/design Cognitive design thinking (produces intent, /illustrate executes)
adobe-execution skill Always-on guardrails (active during this command)
Phase 1: SURVEY
Read the workspace before touching anything. Understand what you have.
For Photoshop
// 1. What documents are open?
get_documents()
// 2. What is the canvas?
get_document_info()
// Record: width, height, resolution, color mode
// 3. What layers exist?
get_layers()
// Record: layer IDs, names, types, visibility, order
For Illustrator
execute_extend_script({
script: `
var doc = app.activeDocument;
var ab = doc.artboards[0].artboardRect;
var items = [];
for (var i = 0; i < doc.pageItems.length; i++) {
var item = doc.pageItems[i];
items.push({
name: item.name,
type: item.typename,
position: item.position,
width: item.width,
height: item.height
});
}
JSON.stringify({
artboard: {
width: ab[2] - ab[0],
height: ab[1] - ab[3],
rect: ab
},
existingItems: items,
itemCount: doc.pageItems.length
});
`
})
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.
- 2d ago First seen · 362 lines · 7 tokens per session scan A 5e0d5551dee0
illustrate is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 2,218 once invoked, about $0.0000 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.