forge-deeplearn

forge-deeplearn is a skill for Claude Code, Codex from ForgeyClap/claude-forge. It costs 47 tokens per session (732 once invoked), scanned A, original, MIT.

A read-only scanner that studies an entire codebase and produces a project summary and risk list. A codebase is the collection of source files that make up a project.

In plain words
What is it for?
Onboarding into projects, preparing product requirements, defining acceptance criteria, and identifying risks before large changes.
Why use it?
It gives an unfamiliar project a documented starting point before planning a major feature, refactor, migration, or architecture change.

Skill for Claude CodeCodex

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 skills/forgeyclap/claude-forge/forge-deeplearn
Any agent
npx skills add ForgeyClap/claude-forge --skill forge-deeplearn
Clone the repo
git clone --depth 1 https://github.com/ForgeyClap/claude-forge

Made for: Claude Code, Codex.

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 forge-deeplearn

README.md
[![agentmods](https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-deeplearn.svg)](https://agentmods.dev/skills/forgeyclap/claude-forge/forge-deeplearn)
Your own site
<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-deeplearn"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-deeplearn.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 732 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 $0.00047 $0.00732
Opus 5 $0.00023 $0.00366
Sonnet 5 $0.00009 $0.00146
Haiku 4.5 $0.00005 $0.00073

Measured 3d ago against content hash 6447d9821e26, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

forge-deeplearn 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.

.claude/skills/forge-deeplearn/SKILL.md · 34 lines

How it starts

The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Learn Mode (WP2 — full-codebase priming scan)

Deep Learn Mode is an on-demand, read-only scan of the current project (.claude/forge-bin/forge-deeplearn.cjs) that produces an honest project-summary and risk-list BEFORE the Lead commits to a PRD or a big architectural change. It never writes into the scanned tree — its only output is its own artifact under .claude/ (with --store) and optional dashboard events.

When the Lead runs it

  • A new or unfamiliar project (first /forge run, or "gebruik forge voor dit project" on a folder with no memory yet).
  • Before generating a PRD or acceptance criteria for a non-trivial feature.
  • Before a large refactor, migration, or architecture change.
  • Not needed for a 1-2 line fix, or a project already scanned this session — check .claude/forge-artifacts/index.jsonl first.

How

node .claude/forge-bin/forge-deeplearn.cjs --path . --run <run_id> --store
  • --path <dir> — defaults to the current directory.
  • --run <run_id> — logs deep_learn_started / deep_learn_completed to that run's dashboard events (omit to run standalone).
  • --store — persists the full result via forge-store.cjs (.claude/forge-artifacts/deeplearn-<epoch>.json).

What it outputs

Stack (node/python/go/rust/dotnet/php/static + framework hints from package.json deps), file counts by category, likely entry points, tests presence, the 5 largest code files, and a risk-list (high/med/low) covering missing tests, oversized files (>800 lines), a missing README, TODO/FIXME density, secret-looking strings, and an unignored .env. Feed the summary + risks straight into the PRD's acceptance criteria, and hand any high risk to the Security Boss / security-reviewer.

Honesty rule (non-negotiable)

  • Read-only. It only ever reads files under --path; it never edits, deletes, or writes into the scanned project. Its only write is the explicit --store artifact under .claude/forge-artifacts/.
  • Real findings only — every risk is backed by an actual file/pattern match; nothing is invented.
  • Never prints or stores a raw secret. A secret-looking match is reported as {file, pattern_name} only, never the matched text — forge-store.cjs's own redaction is a second safety net when --store is used.

Read the full file on GitHub · 34 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. 3d ago First seen · 34 lines · 47 tokens per session scan A 6447d9821e26

Subscribe to this mod's changes

forge-deeplearn is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 732 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.