start-generation

start-generation is a skill for Claude Code from JNZader/repoforge. It costs 29 tokens per session (398 once invoked), scanned A, original, MIT.

Guidance for routes that start, stream, cancel, download, and preview content-generation tasks. A route is an API endpoint that handles a particular operation.

In plain words
What is it for?
Use it when creating generation endpoints, starting a task, streaming its updates, and handling related generation actions.
Why use it?
It provides a defined flow for starting long-running generation work and sending progress updates while it runs.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python apps/server/app/main.py.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote 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.

agentmods badge for start-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/jnzader/repoforge/generate.svg)](https://agentmods.dev/skills/jnzader/repoforge/generate)
Your own site
<a href="https://agentmods.dev/skills/jnzader/repoforge/generate"><img src="https://agentmods.dev/badge/skills/jnzader/repoforge/generate.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 398 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00398
Opus 5 $0.00015 $0.00199
Sonnet 5 $0.00006 $0.00080
Haiku 4.5 $0.00003 $0.00040

Measured 6d ago against content hash bb5d6491df9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

start-generation 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 6d 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.

.claude/skills/backend/generate/SKILL.md · 84 lines

What it actually says

start-generation

This skill covers the generation routes for starting, streaming, canceling, downloading, and previewing.

Trigger: When generating content.

Quick Reference

Task Pattern
Start generation start_generation()
Stream generation stream_generation()

Critical Patterns (Summary)

  • Start Generation: Initiates the generation process.
  • Stream Generation: Streams the ongoing generation process.

Critical Patterns (Detailed)

Start Generation

Initiates the generation process by calling the start_generation function.

from apps.server.app.routes.generate import start_generation

result = start_generation(data)

Stream Generation

Streams the ongoing generation process using the stream_generation function.

from apps.server.app.routes.generate import stream_generation

for chunk in stream_generation(generation_id):
    process_chunk(chunk)

When to Use

  • When a user requests to start a new generation task.
  • When streaming updates for a long-running generation process.

Commands

docker-compose up
python apps/server/app/main.py

Anti-Patterns

Don't: Start without validation

Starting a generation without validating input can lead to errors and unexpected behavior.

# BAD
start_generation(None)
Changes

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.

  1. 6d ago First seen · 84 lines · 29 tokens per session scan A bb5d6491df9a

Subscribe to this mod's changes

start-generation is a skill published in the GitHub repository JNZader/repoforge (5 stars, last pushed 12d ago), licensed MIT. It adds 29 tokens to every session and 398 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.

Related

Other skills, from other repositories