A command that turns a user's suggestion, praise, or criticism into a pre-filled GitHub feedback issue. GitHub is a website for hosting code and tracking project work.

It drafts an issue from the user's message and conversation context, then prints a URL with the title and body filled in for review. The user submits it on GitHub.

It separates improvement ideas and general feedback from reports about something being broken, making each easier to review.

model — Command by vladm3105

Install

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.

agentmods

npx agentmods add commands/vladm3105/aidoc-flow-framework/model

Clone the repo

git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework

Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,118 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.

Model	Per session	Once invoked
Fable 5	$0.00030	$0.01118
Opus 5	$0.00015	$0.00559
Sonnet 5	$0.00006	$0.00224
Haiku 4.5	$0.00003	$0.00112

Measured 2d ago against content hash 857629ce19b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

model 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.

platforms/claude-code-plugin/commands/model.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model

Focused editor for the model.* keys of .claude/aidoc-flow.config.yaml. Records the user's preferred model per SDD layer and the precheck strictness. For the full schema and every other setting, see ${CLAUDE_PLUGIN_ROOT}/docs/CONFIG.md or run /aidoc-flow:configure.

Honest caveat (read this first)

This command is advisory. The plugin cannot switch the Claude Code session model. The session model is set by the user via Claude Code's native /model <id> command. Plugin commands and skills run on whatever model the session is currently on, full stop.

What this command actually does:

Records the user's preferred model per layer in the config file.
Prints the copy-paste /model <id> commands so the user can switch manually when starting work on each layer.
Sets the precheck mode the layer autopilots consult to decide how prominently to surface the per-layer recommendation before drafting. (The plugin cannot read or switch the session model, so the autopilots print the recommendation — they do not compare against the current model.)

Naming note: the user invokes this as /aidoc-flow:model, which is namespaced and does not collide with Claude Code's built-in /model.

Instructions

Read current state — load .claude/aidoc-flow.config.yaml if it exists; otherwise start from the defaults documented in ${CLAUDE_PLUGIN_ROOT}/docs/CONFIG.md.
Print the caveat banner (one paragraph; reuse the language above so the user sees it inside the command, not only in this file).
Prompt for the default model — AskUserQuestion (free text or single-select if you offer a curated short list):
- Current value (from config or default claude-sonnet-4-6) — keep
- A free-text field for any model id that Claude Code's native /model accepts
Do not validate the id against a hard-coded list; new models ship faster than this command updates.
Offer per-layer overrides — AskUserQuestion (yes/no): "Set a different model recommendation for specific layers? (e.g. Opus for BRD and IPLAN, default for the rest.)"

Read the full file on GitHub · 118 lines

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.

2d ago First seen · 118 lines · 30 tokens per session scan A 857629ce19b3

Subscribe to this mod's changes

model is a command published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 1,118 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.

active config

model

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Model

Honest caveat (read this first)

Instructions

What this file has done since we first saw it

Other commands, from other repositories

setup

publish

bump

rebase

git

checklist