extract-conventions

extract-conventions is a command for coding agents from AcKeskin/contexture. It costs 40 tokens per session (292 once invoked), scanned A, original, MIT.

A command that observes how a codebase is written and records its recurring conventions in a project rules file. Conventions are patterns such as naming, imports, comments, and coding style.

In plain words
What is it for?
Use it on a directory, module, or programming language to review detected conventions and save the ones you accept.
Why use it?
It helps new changes match the existing code instead of applying generic or conflicting styles.

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/ackeskin/contexture/extract-conventions
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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 extract-conventions

README.md
[![agentmods](https://agentmods.dev/badge/commands/ackeskin/contexture/extract-conventions.svg)](https://agentmods.dev/commands/ackeskin/contexture/extract-conventions)
Your own site
<a href="https://agentmods.dev/commands/ackeskin/contexture/extract-conventions"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/extract-conventions.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 292 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 $0.00040 $0.00292
Opus 5 $0.00020 $0.00146
Sonnet 5 $0.00008 $0.00058
Haiku 4.5 $0.00004 $0.00029

Measured 3d ago against content hash 3e5c827368ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

extract-conventions 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 3d 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.

commands/extract-conventions.md · 16 lines

What it actually says

Run the extract-conventions skill for the current context.

/extract-conventions <scope> observes a scope (a directory, module, or language) and authors a project-tier conventions.md capturing its dominant, confidently-observed conventions. Examples:

  • /extract-conventions — prompts for a scope.
  • /extract-conventions src/auth/ — extracts conventions from that subtree.
  • /extract-conventions csharp — extracts the C# conventions across the project.

The skill samples representative files, detects mechanical conventions deterministically (case style, prefixes, import ordering) and semantic conventions by model judgment (comment style, idioms — flagged lower-confidence), presents them grouped by category with evidence and confidence, and writes nothing until you accept/edit/reject per category. On accept it writes <project>/.claude/rules/<lang>/conventions.md (project rule tier), delegating the idiomatic prose to the scope's language-pro agent. A convention that contradicts a shipped universal rule is flagged at confirm time — never silently overridden.

Mode A only — never auto-fires. See ~/.claude/skills/extract-conventions/SKILL.md for the full procedure.

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. 3d ago First seen · 16 lines · 40 tokens per session scan A 3e5c827368ba

Subscribe to this mod's changes

extract-conventions is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 292 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.