samugit83

Use before reporting that a change is complete

Use when a test fails after your change

Use after changing the parameters or return of a function

Use after finishing an edit, before moving on to the next one

Use at the start of any task, before making the first edit

Use before adding a new Python module to a package

Use before editing any Python file

Use before reporting that a change is complete

Agent in the Loop: the pseudo-model loop/mcp makes every model call of a chat run a step that an external MCP client (Claude Code, Codex) answers over the inbound MCP server. A loop model must answer only inside its own run scope, never wait outside one,…

Adding an LLM provider to RedAmon: the credential boundary (keys must never reach scan containers), prefix-routed model ids, and the provider registry. A misrouted model id or a leaked key are the two failures this guards. Trigger: adding or editing an LLM…

Adding, removing or changing a tool on RedAmon's INBOUND MCP server, where external agents connect in with a personal access token. The wiki API reference is generated from the server's live tools/list and goes stale silently, and each tool's annotations and…

Adding a new tool to the recon pipeline: the enrichment-module contract and its isolated wrapper (the actual fan-out and test call path), graph completeness, and the preset catalog that silently strips unknown settings. Miss the isolated wrapper and the tool…

Spawning and hardening scan containers from the recon orchestrator: the security flags that look correct and break the container, and the sibling bind-mount path handling. cap_drop and no-new-privileges were each reverted after breaking real scans. Trigger:…

The Priority Board's three-layer score model (rules BASE, REVIEW by the built-in AI or an MCP agent, a person's DECISION) and who may write which layer. A writer that sets a final score itself, or touches another layer, silently undoes a review or a person's…

Adding a Community Agent Skill: a Markdown attack-workflow file that users import from the catalog, which then competes in the Intent Router and is injected into the agent's system prompt. No Python, no rebuild - but it must name only real tools and stay…

Adding a built-in Agent Skill (an attack technique like ssrf, xxe, rce) that ships hardcoded in RedAmon: classified by the Intent Router, injected into the agent prompt, toggled per project, badged in the chat drawer. Ten layers across agentic and webapp, two…