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 rules/dhevenddra/forensic-deepdive/codebasegit clone --depth 1 https://github.com/Dhevenddra/forensic-deepdiveWhat 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 | $0.00196 | $0.00196 |
| Opus 5 | $0.00098 | $0.00098 |
| Sonnet 5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
codebase 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 yesterday.
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.
What it actually says
Codebase brief for AI agents
This repository has a forensic deep-dive. Read docs/codebase/AGENT_BRIEF.md first — it is the headline brief for AI coding agents.
Deeper detail lives alongside it: MAP.md, HOTPATHS.md, ARCHAEOLOGY.md, MENTAL_MODEL.md.
Five single-intent skills under .claude/skills/codebase-*/ tell Claude Code which artifact to consult for which question. An MCP server (forensic serve) exposes nine composite tools (impact, context, archaeology, flow, query, record_insight, recall_insights, visualize, trace) for agents that prefer programmatic queries.
Generated by forensic-deepdive — regenerate with forensic update. Delete this file to opt out.
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.
- yesterday First seen · 15 lines · 196 tokens per session scan A eb278f1b2c61
codebase is a cursor rule published in the GitHub repository Dhevenddra/forensic-deepdive (2 stars, last pushed 16d ago), licensed Apache-2.0. It adds 196 tokens to every session, about $0.0010 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 2026-08-31.
Other cursor rules, from other repositories
cursorrules
Graph: 451 nodes, 1005 edges | 96% extracted, 4% inferred View: general.
cursorrules
When the user asks you to generate diagrams, analyze code structure, or visualize architecture, follow this analysis pipeline. Use terminal commands (rg, find, cat) for all file operations.
cursorrules
Symbiote bonds with your AI tools — giving them memory, context, and your coding DNA.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
dev_workflow
Guide for using Taskmaster to manage task-driven development workflows.
execution
Repository execution and verification commands.