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-reportnpx skills add ForgeyClap/claude-forge --skill forge-reportgit 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-report)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-report"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-report.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 | $0.00040 | $0.02219 |
| Opus 5 | $0.00020 | $0.01110 |
| Sonnet 5 | $0.00008 | $0.00444 |
| Haiku 4.5 | $0.00004 | $0.00222 |
Grade A, and why
forge-report 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge delivery report
Be concrete and honest; reflect only checks that actually ran. Never claim agents/Codex/tests/preview that did not really happen. Do not say "done" if it isn't. Include all sections below.
1. Classification
task type · complexity (L#) · START NEW or CONTINUE · active project folder · fan-out level used.
2. Project Adaptation
detected project type (incl. any custom taxonomy for unknown project types) · detected stack · selected agents · custom subagents created (+ why) · optional agents · agents not used and why · playbooks loaded · why this team fits the project.
2b. Mission Blueprint + Skill Discovery
- Blueprint: one-line expanded mission · quality target · do-not-touch list · definition of done.
- Skill Discovery: required capability areas · skills selected · skills assigned to subagents · custom skills created (path) · skills not selected + why · missing skills · fallback plan. Confirm every executable subagent had an assigned skill/method (or honest BLOCKED).
3. What was done
Plain summary.
4. Files changed
Paths (all inside the project), one-line note each.
5. Checks/tests run
Actual commands + results only. No fabricated output.
6. Agent Activity Ledger (required table — evidence, no fake claims)
Each row has a Runtime (ECC agent · ECC skill · native/main · Codex) and a Status. Statuses ONLY: ECC REAL INVOKED · ECC SKILL LOADED · NATIVE AGENT INVOKED · INTERNAL ROLE ONLY · NOT USED · FAILED · BLOCKED.
| Agent | Custom? | Runtime | Skill / source | Status | Project role | Task | Files read | Files changed | Evidence | Result |
|---|
If a real ECC subagent was dispatched → ECC REAL INVOKED (Runtime = ECC agent). If an ECC skill/playbook ran → ECC SKILL LOADED (Runtime = ECC skill). If a native/main-session agent did the work as a labeled fallback → NATIVE AGENT INVOKED (Runtime = native). A thinking role → INTERNAL ROLE ONLY. ECC tried but unavailable/blocked → BLOCKED. Mark Custom? = yes for Lead-created custom roles and give the assigned Skill / source (ecc-skill/forge-skill/project-local/native/internal). Never label a native role as ECC, or claim a custom subagent/skill that wasn't really created. Don't claim parallel agents unless they really ran separately. Evidence = command output / file diff / tool result / commit hash / log line / created file — or an explicit note that evidence is unavailable and why.
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 · 108 lines · 40 tokens per session scan A 27fd59c2534b
forge-report is a skill published in the GitHub repository ForgeyClap/claude-forge (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 2,219 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.
prototype-web
可点击的功能性 Web 原型, 含导航、英雄区、特性区、CTA.
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.
waitlist-page
【模板: 等候名单页 / Waitlist】 【意图】为新产品 / 早鸟内测做一张极简等候页。 【布局】.
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…