Borrowing it
Nothing to install: this file belongs to JustinPerea/midjourney-cc-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JustinPerea/midjourney-cc-skill/main/.claude/commands/new-session.mdgit clone --depth 1 https://github.com/JustinPerea/midjourney-cc-skillWrote 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/justinperea/midjourney-cc-skill/new-session)<a href="https://agentmods.dev/commands/justinperea/midjourney-cc-skill/new-session"><img src="https://agentmods.dev/badge/commands/justinperea/midjourney-cc-skill/new-session/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/commands/justinperea/midjourney-cc-skill/new-session"><img src="https://agentmods.dev/badge/commands/justinperea/midjourney-cc-skill/new-session.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 | $0.00000 | $0.03871 |
| Opus 5 | $0.00000 | $0.01936 |
| Sonnet 5 | $0.00000 | $0.00774 |
| Haiku 4.5 | $0.00000 | $0.00387 |
Grade A, and why
new-session scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -o sessions/{id}/reference-1.png <url> How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Session
Start a new prompt engineering session with full knowledge application.
Instructions
-
Verify database access. Run
SELECT COUNT(*) FROM sessionsvia sqlite-simple MCP. If the query fails, tell the user: "Database not available. Runclaude mcp add sqlite-simple -- npx @anthropic-ai/sqlite-simple-mcp mydatabase.dbthen restart Claude Code." Do not proceed without database access. -
Gather the user's intent:
- What are they trying to create?
- Do they have a reference image? They can share the image, describe it in text, or both.
- Any specific requirements (aspect ratio, style, mood, use case)?
-
Check for unreflected sessions before starting new work:
SELECT id, intent, total_iterations, status FROM sessions WHERE status IN ('success', 'abandoned') AND reflected = 0If any unreflected sessions exist:
- For each, run the lightweight reflection extraction (see "Session Lifecycle & Automatic Reflection" in
rules/learn-reflection.md) - Mark each session as
reflected = 1 - Briefly inform the user: "Extracted patterns from N previous session(s) before starting."
Also check for sessions left in 'active' status that aren't the current one:
SELECT id, intent, total_iterations FROM sessions WHERE status = 'active'If found, ask the user: should these be marked as abandoned (triggers reflection) or are they still in progress?
- For each, run the lightweight reflection extraction (see "Session Lifecycle & Automatic Reflection" in
-
Analyze the reference — image(s), text, or both:
If the user shares a single reference image:
- Look at it and produce the full reference analysis: subject, lighting (type, key light, fill, rim, atmosphere), colors (palette, temperature, saturation), material/texture, composition (framing, subject position, depth, negative space), mood, style, render quality.
- Think about it from a prompt-engineering perspective: what makes this image look this way, what would be hardest to reproduce in MJ, what could MJ misinterpret, and what keywords map to each visual quality.
- Map visual qualities to prompt language using the keyword effectiveness database.
- Present your analysis to the user. Let them correct, confirm, or add context that the image alone doesn't convey.
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 · 257 lines · 0 tokens per session scan A a7f7d423b003
new-session is a command published in the GitHub repository JustinPerea/midjourney-cc-skill (12 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,871 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
gen-image
Generate a brand-aligned AI image — tool selection, full prompt (subject, style, lighting, camera, mood, negatives), variation prompts, and seed strategy. Works across Midjourney, DALL-E, Ideogram, Firefly, and Stable Diffusion.
music-suno-prompt
Grounded Suno prompt synthesis from local knowledge corpus + persona canon + label canon. No vibes-prompting.
start-3-1-3
Module 3.1.3: Consistency & Style - Golden Rules of prompting, reference images, and variants.
develop-image-prompt.eval
Generates a detailed image generation prompt from a document or content description. Good output: a prompt that is specific, visual, non-abstract, includes style/composition/lighting guidance, and is calibrated to the specified dimensions and style options.
stardust-use
A command for retrieving an encrypted prompt template from a service, decrypting it in memory, filling in parameters, and generating content. It requires an authenticated session.
pickle-prompt
Build a model-ready image/video prompt with the macro-pickle Prompt Engine and (on export) save it to your prompt vault.