RedAmon is an AI framework that connects reconnaissance, exploitation, and post-exploitation activities into an automated security-testing pipeline, while organizing findings and proposing code fixes. It is for authorized penetration testing, security research, and education. The catalogue entries provide skills and instructions for working with the framework.
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 samugit83/redamon --skill recon-ai-enrichmentgit clone --depth 1 https://github.com/samugit83/redamonWrote 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/samugit83/redamon/recon-ai-enrichment)<a href="https://agentmods.dev/skills/samugit83/redamon/recon-ai-enrichment"><img src="https://agentmods.dev/badge/skills/samugit83/redamon/recon-ai-enrichment/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/samugit83/redamon/recon-ai-enrichment"><img src="https://agentmods.dev/badge/skills/samugit83/redamon/recon-ai-enrichment.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 | $0.00137 | $0.01317 |
| Opus 5 | $0.00068 | $0.00659 |
| Sonnet 5 | $0.00027 | $0.00263 |
| Haiku 4.5 | $0.00014 | $0.00132 |
Grade A, and why
recon-ai-enrichment 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 11d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
- Adding AI decision-making to an existing recon tool (tag selection, extension guessing, WAF classification, etc.).
For adding a whole new recon tool, use recon-tool-integration. For the setting
that toggles it, use project-settings-cascade.
Critical Rules
- NEVER let the AI helper raise. Every failure path returns the user's
current value. Recon stdout tails into the webapp's SSE recon drawer, so an
exception both breaks the scan and blanks the stream. Pattern:
recon/helpers/ai_planner/nuclei_tags.py:94
("Never raises -- returns
current_tagson any failure"). - NEVER fall back to an empty list/string. For tools where empty means "skip
the work" (nuclei tags, ffuf extensions) that silently turns detection off.
Fall back to the user's current value, not
[]/"". - NEVER call the LLM with no signal. Empty fingerprint -> return the current value; do not send an empty prompt.
- NEVER hook the AI separately in partial recon. Most tools share one entry
function (e.g.
run_vuln_scanis called by bothmain_recon_modules/andpartial_recon_modules/); hook it once and both paths inherit.grepthe function name to confirm before you edit. The feature must work in the full pipeline AND partial recon. - NEVER touch webapp/src/lib/recon-presets/presets/:
the
aiInPipelinecascade (apply_ai_pipeline_overrides, recon/project_settings.py:1968) is the single source of truth for per-tool AI flags. Presets must not hard-code them; update the Zod schema instead. - ALWAYS cache a per-target hook keyed by tech fingerprint (Server, X-Powered-By, ...) so N targets behind one stack collapse to one LLM call (ffuf_extensions.py). A per-scan hook (nuclei_tags.py) runs once and needs no cache.
- ALWAYS put the toggle in two places bound to the same field
data.{tool}Ai{Feature}: the master AI-in-Pipeline panel (TargetSection.tsx:362) and the tool's own section (e.g. NucleiSection.tsx). Read AND write the same field; no copy-on-flip (they stay in sync because they share the field).
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.
- 11d ago First seen · 92 lines · 137 tokens per session scan A 82707a092884
recon-ai-enrichment is a skill published in the GitHub repository samugit83/redamon (2,416 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 1,317 once invoked, about $0.0007 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
conducting-external-reconnaissance-with-osint
Conducts external reconnaissance using Open Source Intelligence (OSINT) techniques to map an organization's external attack surface without directly interacting with target systems. The tester gathers information from public sources including DNS records, certificate transparency logs, search engines, social media…
conducting-network-penetration-test
Conducts comprehensive network penetration tests against authorized target environments by performing host discovery, port scanning, service enumeration, vulnerability identification, and controlled exploitation to assess the security posture of network infrastructure. The tester follows PTES methodology from…
ai-llm-security-review
Use for AI/LLM security assessments, prompt injection, RAG security, agent/tool permissioning, model supply chain, LLM red teaming, AI governance, eval design, data leakage, jailbreak testing, and secure AI application review.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
deepstream-sop
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the…
cupynumeric-migration-readiness
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment…