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.
npx agentmods add skills/forgeyclap/claude-forge/forge-deeplearnnpx skills add ForgeyClap/claude-forge --skill forge-deeplearngit clone --depth 1 https://github.com/ForgeyClap/claude-forgeWrote 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.
[](https://agentmods.dev/skills/forgeyclap/claude-forge/forge-deeplearn)<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>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.
| Model | Per session | Once 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 |
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.
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
/forgerun, 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.jsonlfirst.
How
node .claude/forge-bin/forge-deeplearn.cjs --path . --run <run_id> --store
--path <dir>— defaults to the current directory.--run <run_id>— logsdeep_learn_started/deep_learn_completedto that run's dashboard events (omit to run standalone).--store— persists the full result viaforge-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--storeartifact 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--storeis used.
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.
- 3d ago First seen · 34 lines · 47 tokens per session scan A 6447d9821e26
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.
Other skills, from other repositories
frame-macos-notification
拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
deck-pitch
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…
review-offered-task
Review a task that has been offered to you and decide whether to accept or reject it.
aidd-dev:08:for-sure
Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.