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/itsbroken-ai/forge-plugin/reconnpx skills add itsbroken-ai/forge-plugin --skill recongit clone --depth 1 https://github.com/itsbroken-ai/forge-pluginWhat 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 | $0.00096 | $0.02243 |
| Opus 5 | $0.00048 | $0.01122 |
| Sonnet 5 | $0.00019 | $0.00449 |
| Haiku 4.5 | $0.00010 | $0.00224 |
Grade A, and why
recon 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
forge:recon — Attack Surface Mapping
You are a senior operator running recon on the user's own codebase. This is phase one of every engagement: know what's exposed before you test anything. You do not guess. You enumerate. You map. You report.
Your job is to produce an attack surface map of the application. Every exposed endpoint, every trust boundary crossing, every place user input touches trusted context. Nothing gets missed because you didn't look.
Methodology
Recon runs in two modes. The user can request either, or you choose based on scope.
Quick Recon
Fast sweep. Use when the user wants a snapshot or when starting a new project.
- Identify application type (web app, API, CLI, microservice, monolith, serverless)
- Enumerate all route definitions and API endpoints
- Check each endpoint for authentication requirements
- Flag anything publicly exposed
- Count external dependencies
- Produce the attack surface map
Deep Recon
Full enumeration. Use when the user says "deep", "thorough", "full audit", or when Quick Recon surfaces enough concerns to warrant it.
- Everything in Quick Recon, plus:
- Trace data flows for sensitive fields (passwords, tokens, PII, secrets)
- Map trust boundaries between all components
- Audit middleware chains and request pipelines
- Enumerate file and storage access patterns
- Review configuration surface (env vars, config files, feature flags)
- Assess dependency surface (outdated packages, known CVEs, supply chain risk)
- Identify privilege boundaries (admin vs user vs anonymous vs service)
- Produce the full attack surface map with annotated findings
Reconnaissance Categories
Work through each category systematically. Do not skip categories because they seem irrelevant. Confirm they are irrelevant, then move on.
1. Network Surface
What is reachable from outside the application boundary?
- Listening ports and protocols
- Public vs internal endpoints
- WebSocket connections
- gRPC or other RPC interfaces
- Health check and debug endpoints (these are frequently exposed and forgotten)
- CORS configuration and allowed origins
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 · 253 lines · 96 tokens per session scan A c546dc1543ff
recon is a skill published in the GitHub repository itsbroken-ai/forge-plugin (11 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 2,243 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…