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 agent-in-the-loopgit 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/agent-in-the-loop)<a href="https://agentmods.dev/skills/samugit83/redamon/agent-in-the-loop"><img src="https://agentmods.dev/badge/skills/samugit83/redamon/agent-in-the-loop/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/agent-in-the-loop"><img src="https://agentmods.dev/badge/skills/samugit83/redamon/agent-in-the-loop.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 | $0.00150 | $0.01313 |
| Opus 5.5 | $0.00060 | $0.00525 |
| Sonnet 5.5 | $0.00030 | $0.00263 |
| Haiku 4.5 | $0.00015 | $0.00131 |
Grade A, and why
agent-in-the-loop 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 today.
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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
- Changing the step broker, the adapter, the prompt document or the
/loop/*routes. - Adding a model call to the agent, or a loop that retries model calls.
- Adding any endpoint, job or feature that builds a chat model from a model id.
- Changing the loop MCP tools, their scope, the driver-token rule, or the drawer's loop status.
Critical Rules
- A loop model answers ONLY inside a live run scope of its session that uses the loop.
Its identity comes from
get_broker().scope_for_session(current_log_session_id), never fromcurrent_user_id,current_project_idorcurrent_session_id: initialize_node calls the guardrail and the classifier before any node sets those (model.py, agent_context.py). - A new path that builds an LLM from a model id refuses
loop/withrefuse_loop_model()/LoopModelNotSupportedHere(codeloop_model_not_supported_here): no chat run, no driver, a wait that never ends (llm_builder.py, theapi.pybuilders). Feature pickers filter it withexcludeLoop, saves refuse it. - Loop errors are never retried. They carry
no_retry = Trueand their messages contain no transient phrase (timeout,connection, a bare 5xx);is_transient_llm_errorchecks the marker first. A new loop that retries on ANY exception mustbreakongetattr(e, "no_retry", False)(errors.py, phase.py is the example). - A new model call site gets an
llm_purpose(...)label, or its step reaches the driver asotherwith atextanswer format (purpose.py). - Dangerous tools always ask a person in a loop run. Read the setting through
confirmation_required(get_setting('REQUIRE_TOOL_CONFIRMATION', True)), never directly. - Only a person answers approvals, questions and dangerous-tool confirmations. No MCP tool may answer them (loopTools.ts).
- A driver token holds no write or exec scope besides
agent:loop. Compute it fromMCP_SCOPE_COPYwithloopTokenProblem, never a hand list; the loop tools refuse wider tokens (loopScopes.ts). - A person picks the brain. MCP writes, presets, imports and user defaults never set a
loop model (
loopModelRefusal, the preset checks,rememberedDefaults). - Any change to the step shape bumps
contractVersion(agentCONTRACT_VERSION, the skill pack'sLOOP_CONTRACT_VERSION), so a client's out-of-date skill says so. - A new loop tool joins
LOOP_TOOL_NAMES(withdrawn while the switch is off), every MCP test that stubsMCP_KALI_EXEC_ENABLEDalso stubsAGENT_IN_THE_LOOP_ENABLED, thennpm run docs:mcp(themcp-server-toolsskill). loop_statusand the step views carry no prompt or answer text; the WebSocket frame is sent, never persisted.
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.
- today First seen · 84 lines · 150 tokens per session scan A aa951e9a8a42
agent-in-the-loop is a skill published in the GitHub repository samugit83/redamon (3,277 stars, last pushed yesterday), licensed MIT. It adds 150 tokens to every session and 1,313 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-11-04.
Other skills, from other repositories
codex-autoresearch
Triage improvement work and run or resume accepted measured loops in a local project. Architecture, documentation, UX, product study, open research, taste, and one-shot fixes stay direct unless the user explicitly requests repeated measurement with a complete experiment contract.
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, or model upgrade and prompt-upgrade guidance; use OpenAI docs MCP tools for non-Codex docs…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.
competitor-research
Research a competitor across the web and produce a cited, structured brief.
ad-attacks
Active Directory attack reference — BloodHound Cypher queries, Kerberos attack decision tree, ACE/ACL abuse, ADCS ESC1-8, and AD misconfig checklist.
wordlists
SecLists path map, hashcat rules, CeWL usage, and custom wordlist generation for all attack categories.