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 skills add qte77/claude-code-plugins --skill web-recongit clone --depth 1 https://github.com/qte77/claude-code-pluginsWrote 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/qte77/claude-code-plugins/web-recon)<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/web-recon"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/web-recon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/web-recon"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/web-recon.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.00988 |
| Opus 5.5 | $0.00020 | $0.00395 |
| Sonnet 5.5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
web-recon scanned grade A with 1 finding 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 21d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Produce a **provenance-tagged** report: which tool established each fact (curl / WebFetch / How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web / API Reconnaissance & Assessment
Target: $ARGUMENTS
Drive the web-recon-kit harness to enumerate and assess a web/API target. Every
target-specific detail lives in scope.toml; the runners are read-only (GET/OPTIONS), throttled,
and never trigger cron/mutation endpoints.
0. Authorization gate (MANDATORY)
Before ANY request to the target, confirm the user owns or is explicitly authorized to test it — their own workspace/account, a written pentest scope, an in-scope bug-bounty program, or a CTF. If authorization is unclear, STOP and ask. Refuse targets the user does not control. Never run against a third party "just to see."
1. Set up the target profile
- Ensure a
web-recon-kitcheckout is available, then runmake setup, plusmake setup-browserfor the browser tier (installs polyfetch from GitHub + chromium viauv sync --extra browser). cp scope.example.toml scope.toml, then fill in:base_url;[identities.*].env(env-var NAMES holding the API keys — keys live in.env, never inscope.toml);[recon].routes,[authmatrix].public_ok,[bfla].admin_prefixes,[[bola.collectors]].
2. Passive enumeration (no auth)
make inventory— mine/api/*endpoints from the JS bundles.make recon— render each route, classify its gate (public / client-side / server-middleware), capture screenshots. Both needmake setup-browser.- Record anything reachable without authentication.
3. API testing (owner identity)
make authmatrix— every endpoint × every configured identity, GET-probed → auth-posture matrix; flag unauthenticated 200s on non-public paths (then body-check them — an empty/generic 200 is not a leak).make cron— confirm cron endpoints reject unauthenticated requests.
4. Authorization / tenant isolation
make bola— cross-tenant IDOR (Insecure Direct Object Reference), a.k.a. BOLA (Broken Object-Level Authorization): collect owner resource IDs, replay them as a second tenant (tenant_b). A 200 == cross-tenant leak. Needs a 2nd tenant identity.make bfla— BFLA (Broken Function-Level Authorization): probe admin / RBAC (Role-Based Access Control) endpoints as a low-role member; any success is privilege escalation.
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.
- 21d ago First seen · 84 lines · 51 tokens per session scan A 8acd2bdc8056
web-recon is a skill published in the GitHub repository qte77/claude-code-plugins (3 stars, last pushed 4d ago), licensed Apache-2.0. It adds 51 tokens to every session and 988 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.
Other skills, from other repositories
design-code-architecture
Guided journey from an app idea to a deliberate architecture: boundaries, domain model, data decisions, and resilience, making only the expensive-to-reverse decisions and deferring the rest. Orchestrates eight skills phase by phase - clean-architecture, domain-driven-design, system-design, ddia-systems…
system-design
Design scalable distributed systems using structured approaches for load balancing, caching, database scaling, and message queues. Use when the user mentions "system design", "scale this", "high availability", "rate limiter", "design a URL shortener", "design Twitter", "design Uber", "design a news feed", "system…
go-structure
Recommend and scaffold Go project layouts by type (CLI, API, library, monorepo). Use when starting a Go project, when asked about package organization, or when reviewing structure for anti-patterns (utils packages, over-nesting, misused pkg/).
lark-openapi-explorer
A skill for finding and calling Lark APIs that are not already available through existing commands. An API is a defined way for software to request work from another service.
lark-skill-maker
A guide for creating reusable coding-agent skills that call Feishu APIs through lark-cli. lark-cli is a command-line tool for accessing Feishu operations from a terminal.
scaffold-fastapi-vite-saas
A starter project for a self-hosted web app with a FastAPI Python backend and a Vite single-page frontend in one Git repository. A monorepo is one repository that holds multiple parts of a project.