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/samugit83/redamon/traffic-capturenpx skills add samugit83/redamon --skill traffic-capturegit 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/traffic-capture)<a href="https://agentmods.dev/skills/samugit83/redamon/traffic-capture"><img src="https://agentmods.dev/badge/skills/samugit83/redamon/traffic-capture.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 | $0.00099 | $0.00778 |
| Opus 5 | $0.00049 | $0.00389 |
| Sonnet 5 | $0.00020 | $0.00156 |
| Haiku 4.5 | $0.00010 | $0.00078 |
Grade A, and why
traffic-capture 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
- Changing how the proxy forwards, captures, ingests, or replays traffic.
The one-line "route every egress through the guard" rule is in the capture_proxy AGENTS.md CRITICAL RULES; this skill is the mechanism.
Critical Rules
- NEVER match the internal denylist on the hostname alone. The guard denies on the resolved IP (RFC1918 and friends), because a hostname that resolves to an internal address (or re-resolves after a check) is the SSRF/DNS-rebinding case. See scanners/capture_proxy/egress.py (the block conditions operate on the resolved IP).
- NEVER build a replay/fuzz target from unvalidated LLM output and send it
straight out. The replay path is a new egress path; it must pass the same
EgressPolicyguard as captured traffic, or the agent can be steered into an internal pivot. Args must not reach the wire un-guarded. - NEVER remove a block condition to "make replay work". Each condition is
individually toggleable via
EgressPolicy(surfaced in settings); loosen it there, per-condition, not by deleting the check. - ALWAYS keep capture and ingest off the scan's critical path. Capture writes an append-only spool; a separate worker tails it into Postgres (scanners/capture_proxy/ingest_worker.py). That decoupling is deliberate - capture must never block or slow the scan it observes.
The capture pipeline
| Stage | File | Note |
|---|---|---|
| intercept | capture_addon.py | mitmproxy addon; request/response hooks |
| egress guard | egress.py | resolved-IP denylist + EgressPolicy toggles; the SSRF backstop |
| ingest | ingest_worker.py | tails the spool -> Postgres; off the scan path |
Commands
docker compose --profile tools build capture-proxy # image rebuild (Dockerfile change)
./redamon.sh test unit # capture_proxy section
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 · 68 lines · 99 tokens per session scan A 5902b99566b4
traffic-capture is a skill published in the GitHub repository samugit83/redamon (2,380 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 778 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
workflow-orchestrator
Module Loop and Iteration Skill for orchestrating multi-phase penetration testing workflows. Use when coordinating sequential tool execution, managing dependencies between reconnaissance and vulnerability scanning modules, implementing adaptive fallback strategies, or managing workflow state across iterations.…
poc-validator
Proof-of-Concept (PoC) Validation Skill for security exploit verification. Use when validating exploitability of vulnerabilities, generating tailored payloads, executing exploits in sandboxed environments, or verifying successful exploitation (e.g., SQL injection, CVE exploitation, command injection). Triggers on…
Reconnaissance & OSINT Automation
Passive and active reconnaissance, subdomain enumeration, DNS analysis, technology fingerprinting, and OSINT data correlation for authorized security assessments.
research-orchestrator
Parallel research with 4 specialized agents (Official, Practical, Edge Cases, Future).
tdd-agent
Autonomous test-driven development agent that writes code to make tests pass.
kali-pentest
Execute authorized penetration testing via Kali Linux CLI tools over SSH or Docker. Covers: information gathering, vulnerability analysis, sniffing & spoofing, web/API testing, exploitation, password attacks, wireless, cloud-native security, RFID/NFC, VoIP/ICS, reverse engineering, forensics, post-exploitation/C2, and…