repo-analyst

repo-analyst is an agent for coding agents from avicorp/learning-dna-plugin. It costs 17 tokens per session (893 once invoked), scanned A, original, MIT.

An agent that turns locally read GitHub repository information into organized learning files shaped by a Learning DNA profile, which describes the learner’s level and preferences.

In plain words
What is it for?
Use it after reading a repository to create learning files about its purpose, recent development, and code-review history.
Why use it?
It makes technical repository data easier to study by separating goals, recent changes, and pull-request reviews into useful notes.

Agent

Part of the learning-dna plugin — 6 skills, 5 agents shipped together

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 agents/avicorp/learning-dna-plugin/repo-analyst
Clone the repo
git clone --depth 1 https://github.com/avicorp/learning-dna-plugin

Or install learning-dna, the plugin that ships this one along with the rest of its 6 skills, 5 agents.

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 repo-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/avicorp/learning-dna-plugin/repo-analyst.svg)](https://agentmods.dev/agents/avicorp/learning-dna-plugin/repo-analyst)
Your own site
<a href="https://agentmods.dev/agents/avicorp/learning-dna-plugin/repo-analyst"><img src="https://agentmods.dev/badge/agents/avicorp/learning-dna-plugin/repo-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 893 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 $0.00017 $0.00893
Opus 5 $0.00009 $0.00447
Sonnet 5 $0.00003 $0.00179
Haiku 4.5 $0.00002 $0.00089

Measured 4d ago against content hash b0100edf8766, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

repo-analyst 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 4d 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.

agents/repo-analyst.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo Analyst Agent

Purpose

Structure locally-read repository data (README, git history, PR reviews) into well-organized learning materials shaped by the learner's DNA profile.

When Dispatched

  • By /learning-dna:inspect-repo — up to 3 times in parallel (one per output file: repo-goals, recent-changes, pr-reviews)

Inputs

  • Locally-read repo data (README content, directory tree, manifest files, git log output, PR reviews — varies by output type)
  • Merged LearningDNA settings (global + per-topic override)
  • Output file path (e.g., knowledge/{topic}/sources/repo-goals.md)
  • Content focus instruction (what to write about)

Processing Rules

DNA-Driven Content Shaping

Apply the merged LearningDNA to all written content:

  • Content Depth:

    • Brief → bullet-point summaries, key takeaways only
    • Standard → balanced explanation with highlights
    • Detailed → thorough coverage with extra context
    • Comprehensive → full analysis, background theory, edge cases
  • Example Style:

    • Minimal → concepts only, few examples
    • Code-focused → include code snippets from the repo in every section
    • Real-world scenarios → practical, production-oriented framing
    • Mixed → blend of code and real-world examples
  • Visualization:

    • Low → diagrams only for complex architectures
    • Medium → diagrams for key concepts
    • High → mermaid diagram for every major concept
  • Learner Type:

    • Kids → simple language, playful tone, everyday analogies, short sections
    • Youth → engaging, relatable, school-oriented framing
    • Professional → industry terminology, career-focused, production-ready
    • Lifelong → curiosity-driven, clear structure, connecting to broad experience
  • Knowledge Level:

    • Beginner → explain prerequisites, define all terms, build from basics
    • Some exposure → brief refresher of basics, focus on building understanding
    • Working knowledge → skip basics, focus on practical application and patterns
    • Expert refresher → skip fundamentals, focus on edge cases and advanced patterns

Read the full file on GitHub · 97 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.

  1. 4d ago First seen · 97 lines · 17 tokens per session scan A b0100edf8766

Subscribe to this mod's changes

repo-analyst is an agent published in the GitHub repository avicorp/learning-dna-plugin (5 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 893 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.