Borrowing it
Nothing to install: this file belongs to ForgeyClap/claude-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ForgeyClap/claude-forge/main/.claude/skills/forge-scout/SKILL.mdgit 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-scout)<a href="https://agentmods.dev/skills/forgeyclap/claude-forge/forge-scout"><img src="https://agentmods.dev/badge/skills/forgeyclap/claude-forge/forge-scout.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 5.1 | $0.00047 | $0.01905 |
| Opus 5 | $0.00023 | $0.00953 |
| Sonnet 5 | $0.00009 | $0.00381 |
| Haiku 4.5 | $0.00005 | $0.00191 |
Grade A, and why
forge-scout 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge playbook — Scout (external-capability research + vetting)
Do not duplicate existing tools — defer to: forge-mcp-clients skill (the dormant/opt-in MCP doctrine
every APPROVE verdict here still has to clear before anything is ever wired live), forge-bin/forge-scout.cjs
(the tailored-term generator + persistent vetting ledger this file's doctrine is built on top of), and the
watch skill (the ONLY sanctioned way to actually view a candidate's demo/review video — never described
or summarized from a title/thumbnail alone).
What Scout is for
Per-project research into whether an EXTERNAL capability (a published Claude skill, a Claude Code plugin, an MCP server, or a standalone CLI) would genuinely help the current project — not a generic "are there Claude skills" sweep. A slides project searches for slide/PowerPoint-shaped capabilities; an Astro site searches for Astro/static-site-shaped capabilities. Scout never installs anything itself; it produces a researched, evidenced verdict that the owner opts into afterward.
Step 1 — generate TAILORED search terms, not generic ones
Call forge-bin/forge-scout.cjs terms --domain <domain> [--keywords <k1,k2,...>] first. This returns a
domain-specific term list seeded from the project's actual domain (see the tool's SEED_TEMPLATES for the
curated set: website, astro, slides/presentation, fullstack, n8n, scraping, rag, prediction, integration,
electron/desktop, ecommerce, dashboard, game, mobile, mlops, tooling, voice — plus a domain-tailored fallback
for anything not yet curated). Example of the difference this makes:
- A slides project:
"claude powerpoint skill","claude slide generator skill","I stopped using PowerPoint claude code skill"— not a bare"claude skill"search. - An Astro project:
"claude astro skill","bulk website generator claude"— not a bare"claude plugin"search. Never hand-write ad-hoc terms when the tool's tailored list already covers the domain; extend it with--keywordsfor anything project-specific the curated seed doesn't know about (a client name, a niche library, a specific integration).
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 · 110 lines · 47 tokens per session scan A cdafde149bad
forge-scout 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 1,905 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 2026-09-03.
Other skills, from other repositories
flame-harness-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-contract
Phase 4 — propose verifiable completion criteria and mandatory hard gates; reach AGREED (1-pass default, multi-round negotiation in --strict).
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.