run

A complete workflow for analyzing a software project and creating guidance files for coding agents. It examines the code, improves its automatically found rules, and compiles the results into files such as AGENTS.md and CLAUDE.md.

In plain words
What is it for?
Use it to generate project rules, document code conventions, and update instructions used by tools such as Claude Code, Cursor, GitHub Copilot, and Windsurf.
Why use it?
Generic coding guidance often misses how a particular project is organized. This workflow turns the codebase's own patterns into more specific instructions in one run.

Command

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/sandeepshekhar26/develop-anything/run
Clone the repo
git clone --depth 1 https://github.com/sandeepshekhar26/develop-anything
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 461 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 $0.00032 $0.00461
Opus 5 $0.00016 $0.00230
Sonnet 5 $0.00006 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured 2d ago against content hash 663f0c2e37e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

run 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.

plugins/claude-code/commands/run.md · 39 lines

What it actually says

Run auk end to end so the user gets rich, codebase-specific AI-context files from a single command. You (this agent) are the LLM that does the semantic pass — do not ask the user to copy-paste prompts anywhere.

1. Analyze (deterministic)

Run npx -y auk-develop generate --no-compile --emit-prompts in the project root. This parses the code (tree-sitter), builds the import + call graph, mines conventions, clusters files, writes .auk/rules.yaml and .auk/graph.json, and emits .auk/prompts/enhance-rules-NN.md.

2. Deep pass (you)

Read every .auk/prompts/enhance-rules-NN.md. For each rule, open the cited evidence files and rewrite the description to be specific to THIS codebase — naming real directories, frameworks, types, and functions — plus a rationale for why it exists and what breaks if violated. Be concrete and actionable. Work through batches in parallel where practical. Write each enhance-rules-NN.response.json to match the embedded schema, then run npx -y auk-develop enhance --apply <file> for each.

3. Compile

Run npx -y auk-develop compile to regenerate CLAUDE.md, AGENTS.md, .cursor/rules/*.mdc, .github/copilot-instructions.md, .windsurfrules, .aider.conf.yml, and GEMINI.md from the enhanced rules.

4. Report

Tell the user how many rules were generated and enhanced, the project overview auk detected (stack, entrypoints, directory map), and remind them they can:

  • run auk verify (or auk verify --ci) to catch context rot over time,
  • run auk graph --open to explore the dependency/call graph,
  • commit .auk/rules.yaml, graph.json, and the compiled files.
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. 2d ago First seen · 39 lines · 32 tokens per session scan A 663f0c2e37e8

Subscribe to this mod's changes

run is a command published in the GitHub repository sandeepshekhar26/develop-anything (17 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 461 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 2026-08-30.