Recon Skills is a pack of security-testing skills covering reconnaissance, web applications, APIs, authentication, vulnerability validation, cloud infrastructure, and reporting. Security professionals use it for authorized assessments of systems they own or have written permission to test. The catalogue entries are individual skills from the pack.
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 uphiago/recon-skills --skill recon-playbookgit clone --depth 1 https://github.com/uphiago/recon-skillsWrote 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/uphiago/recon-skills/recon-playbook)<a href="https://agentmods.dev/skills/uphiago/recon-skills/recon-playbook"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/recon-playbook/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/uphiago/recon-skills/recon-playbook"><img src="https://agentmods.dev/badge/skills/uphiago/recon-skills/recon-playbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00018 | $0.01831 |
| Opus 5 | $0.00009 | $0.00915 |
| Sonnet 5 | $0.00004 | $0.00366 |
| Haiku 4.5 | $0.00002 | $0.00183 |
Grade A, and why
recon-playbook 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 12d 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.
compatibility: Requires curl, jq, subfinder, dnsx, httpx, katana, and optional nmap How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External Web Recon Playbook
Use this playbook to turn an authorized root domain or asset list into a prioritized map of web applications, APIs, authentication boundaries, and testable security hypotheses.
scope
-> assets
-> DNS and services
-> routes and client code
-> APIs and identities
-> hypotheses
-> focused validation
-> evidence and reporting
When to Use
- Beginning an external web, API, or bug bounty assessment.
- Recon output exists but lacks normalization, provenance, or prioritization.
- The target spans multiple applications, subdomains, or identity boundaries.
- A broad scan needs to be converted into focused manual validation.
Do not use this playbook to justify activity outside the agreed scope or to run every available tool against every asset.
Prerequisites
- Explicit authorization, target boundaries, exclusions, rate limits, and stop conditions.
curl,jq,subfinder,dnsx,httpx, andkatana.nmaponly when IP or port discovery is in scope.- Approved test identities for authorization and session testing.
- A writable evidence directory.
How to Run
export TARGET="example.test"
export OUTPUT_DIR="${OUTPUT_DIR:-./output/$TARGET}"
mkdir -p \
"$OUTPUT_DIR/assets" \
"$OUTPUT_DIR/http" \
"$OUTPUT_DIR/urls" \
"$OUTPUT_DIR/evidence"
Run each phase only after reviewing the preceding output. Keep raw source files so every hostname, URL, and hypothesis has provenance.
Procedure
1. Record Scope
Keep a short operator-readable scope record beside the output:
allowed: *.example.test
excluded: status.example.test
identities: anonymous, test-user-a, test-user-b
request rate: 2 requests/second/host
state changes: synthetic records only
The scope must answer what may be tested, which identities may be used, how much traffic is acceptable, and whether a state-changing test is allowed.
2. Discover and Normalize Assets
subfinder -d "$TARGET" -silent \
> "$OUTPUT_DIR/assets/subfinder.txt"
curl -sS --max-time 30 \
"https://crt.sh/?q=%25.${TARGET}&output=json" \
| jq -r '.[].name_value' \
| sed 's/^\*\.//' \
> "$OUTPUT_DIR/assets/crtsh.txt"
cat "$OUTPUT_DIR/assets/subfinder.txt" \
"$OUTPUT_DIR/assets/crtsh.txt" \
| tr '[:upper:]' '[:lower:]' \
| grep -E '^[a-z0-9.-]+\.[a-z]{2,}$' \
| sort -u \
> "$OUTPUT_DIR/assets/hostnames.txt"
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.
- 12d ago First seen · 237 lines · 18 tokens per session scan A 39a32800c0c6
recon-playbook is a skill published in the GitHub repository uphiago/recon-skills (1,254 stars, last pushed 10d ago), licensed MIT. It adds 18 tokens to every session and 1,831 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other skills, from other repositories
seedance-pipeline
This skill should be used when the user asks about Seedance 2.0 workflow operations, API planning, BytePlus ModelArk, Dreamina/Jimeng surfaces, provider/router APIs, China-facing surfaces, ComfyUI, post-production, stitching, batch workflow, or integration planning.
seedance-pipeline
This skill should be used when the user asks about Seedance 2.0 workflow operations, API planning, BytePlus ModelArk, Dreamina/Jimeng surfaces, provider/router APIs, China-facing surfaces, ComfyUI, post-production, stitching, batch workflow, or integration planning.
horse-database-pooling
Guide for setting up thread-safe database connection pooling (FireDAC / UniDAC) in multithreaded Horse applications.
horse-mvc-architecture
Guide for structuring corporate Horse applications using Clean MVC (Model-View-Controller) principles and decoupling HTTP layers from business logic.
horse-request-response
Guide to interacting with THorseRequest (body, query, params, headers) and THorseResponse (Send, Status, ContentType).
horse-dependency-injection
Guide for managing request-scoped contextual services and IoC (dependency injection) in Delphi and Lazarus.