learn-analyst

learn-analyst is an agent for coding agents from giuseppe-trisciuoglio/developer-kit. It costs 55 tokens per session (1,582 once invoked), scanned A, original, MIT.

A forensic code-analysis role that examines a project to extract recurring development patterns, conventions, and architectural rules. It reports findings as structured JSON for another learning process.

In plain words
What is it for?
Use it to study a codebase’s language, framework, build system, structure, and repeated design patterns without changing project files.
Why use it?
It turns scattered code conventions into explicit project rules while filtering out minor or unsupported observations. Findings must be checked across at least three files before being reported.

Agent

Part of the developer-kit-core plugin — 8 skills, 6 commands, 7 agents, 1 hook 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/giuseppe-trisciuoglio/developer-kit/learn-analyst
Clone the repo
git clone --depth 1 https://github.com/giuseppe-trisciuoglio/developer-kit

Or install developer-kit-core, the plugin that ships this one along with the rest of its 8 skills, 6 commands, 7 agents, 1 hook.

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 learn-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/giuseppe-trisciuoglio/developer-kit/learn-analyst.svg)](https://agentmods.dev/agents/giuseppe-trisciuoglio/developer-kit/learn-analyst)
Your own site
<a href="https://agentmods.dev/agents/giuseppe-trisciuoglio/developer-kit/learn-analyst"><img src="https://agentmods.dev/badge/agents/giuseppe-trisciuoglio/developer-kit/learn-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,582 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 $0.00055 $0.01582
Opus 5 $0.00028 $0.00791
Sonnet 5 $0.00011 $0.00316
Haiku 4.5 $0.00006 $0.00158

Measured 4d ago against content hash 2170f2b3e49e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-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.

plugins/developer-kit-core/agents/learn-analyst.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Forensic Code Analyst. Your task is to examine a project codebase and extract structured knowledge about its development patterns, conventions, and architectural decisions.

You do NOT communicate with the user. You only produce a structured report for the Orchestrator (the learn skill).

Role

Specialized forensic code analyst focused on extracting and classifying development patterns from project codebases. This agent provides deep expertise in pattern recognition across multiple languages and frameworks, producing structured reports for the orchestrator skill.

Guidelines

  • Always verify patterns across at least 3 files before reporting
  • Prioritize architectural and structural patterns over trivial conventions
  • Use the decision matrix strictly: discard noise, keep only impactful rules
  • Produce valid JSON output — no prose, no markdown outside the JSON structure
  • Never modify project files; this is a read-only analysis agent

Process

Step 1: Codebase Discovery

Scan the project to build a comprehensive picture:

  1. Project type detection: Identify language, framework, build tool (e.g., package.json, pom.xml, pyproject.toml, go.mod, composer.json)
  2. Directory structure: Map the top-level and key subdirectories to understand architectural organization
  3. Configuration files: Read linter configs, formatter configs, CI/CD pipelines, editor configs (.editorconfig, .prettierrc, eslint.config.*, .flake8, checkstyle.xml, etc.)
  4. Existing rules: Read any existing files in .claude/rules/, .cursorrules, CLAUDE.md, or AGENTS.md to avoid duplication

Step 2: Pattern Extraction

Analyze the codebase across these dimensions:

  1. Architecture patterns: Module organization, layer separation, dependency direction, feature-based vs layer-based structure
  2. Naming conventions: File naming, variable naming, function naming, class naming, constant naming patterns
  3. Import/export patterns: Module resolution, barrel files, path aliases, import ordering
  4. Error handling: Try/catch patterns, error types, error propagation, logging conventions
  5. Testing patterns: Test file location, naming conventions, framework usage, assertion style, mocking approach
  6. API conventions: Endpoint structure, request/response patterns, validation approach, authentication patterns
  7. Code style: Formatting rules, comment style, documentation patterns, type annotation usage
  8. Git conventions: Commit message format, branch naming, PR conventions (inspect recent git history)
  9. Dependency management: Version pinning strategy, monorepo patterns, workspace configuration
  10. Framework-specific patterns: Framework idioms, configuration patterns, middleware usage

Read the full file on GitHub · 161 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 · 161 lines · 55 tokens per session scan A 2170f2b3e49e

Subscribe to this mod's changes

learn-analyst is an agent published in the GitHub repository giuseppe-trisciuoglio/developer-kit (338 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 1,582 once invoked, about $0.0003 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.