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-migrationnpx skills add ForgeyClap/claude-forge --skill forge-migrationgit 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-migration)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-migration"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-migration.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 | $0.00042 | $0.01508 |
| Opus 5 | $0.00021 | $0.00754 |
| Sonnet 5 | $0.00008 | $0.00302 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
forge-migration 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.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge playbook — Legacy modernization / migration
Do not duplicate ECC skills — defer to: learn-codebase / forge-deeplearn (prime the legacy system before touching it — mandatory here), test-driven-development + systematic-debugging (characterization + regression work), forge-worktrees (isolate each slice), /test-coverage. This file is orchestration only.
The governing principle is Michael Feathers' rule: you cannot safely change code you cannot characterize. Migration is not a rewrite — it is a sequence of small, reversible, parity-verified swaps behind a facade, each of which keeps the system working the whole time. The catastrophic failure mode is the "big-bang" rewrite that goes dark for months and cuts over into unverified behavior loss. Forge does not do that.
Hard rules
- Characterization tests first. Before changing any legacy behavior, capture what it currently does with characterization / golden-master / approval tests — including the ugly, undocumented, "wrong-but-relied-on" behavior. These pin the existing contract so a migration can prove it preserved it. No behavior change lands before its characterization test exists and passes on the legacy code.
- Strangler-fig, incremental cutover. Introduce a seam / facade / routing layer and move one slice at a time to the new implementation behind it. The old and new systems run side by side; the facade decides per-request which path serves. Never replace the whole thing at once.
- Every step is reversible. Each slice cuts over behind a feature flag / route toggle with a proven route-back. Each step is independently deployable and independently revertible. If a slice misbehaves in production, you flip it back in seconds — you never have to "un-rewrite".
- Parity verified before a slice is trusted. Old vs new must produce the same result: shadow/diff the new path against the old (GitHub-Scientist-style compare, or replayed inputs) and reconcile every discrepancy before the slice takes real traffic. Divergence is investigated, not waved through.
- No big-bang rewrite. No months-long dark rewrite, no "we'll cut over everything on the weekend". If the plan can't be sliced, the first work package is to find the seams that make slicing possible.
- Data migration is reversible and verified. Schema/data moves use dual-write or backfill-then-verify with row-count + checksum reconciliation and a rollback path. The old store stays authoritative until parity is proven; no destructive drop of the source until the new store is verified and a backup exists.
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.
- 4d ago First seen · 39 lines · 42 tokens per session scan A 5daff7b3f3c0
forge-migration is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,508 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.