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 instructions/dhevenddra/forensic-deepdive/agents-mdgit clone --depth 1 https://github.com/Dhevenddra/forensic-deepdiveWrote 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/instructions/dhevenddra/forensic-deepdive/agents-md)<a href="https://agentmods.dev/instructions/dhevenddra/forensic-deepdive/agents-md"><img src="https://agentmods.dev/badge/instructions/dhevenddra/forensic-deepdive/agents-md.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 | $0.00328 | $0.00328 |
| Opus 5 | $0.00164 | $0.00164 |
| Sonnet 5 | $0.00066 | $0.00066 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
forensic-deepdive AGENTS.md 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 3d 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.
What it actually says
AGENTS.md
This file mirrors CLAUDE.md. Single source of truth lives in CLAUDE.md; this file is provided for cross-tool compatibility (Codex CLI, Cursor, Continue, Aider, Factory Droid, Gemini CLI, GitHub Copilot CLI, Jules, VS Code) since the Linux Foundation's Agentic AI Foundation (December 2025) standardized on AGENTS.md.
Read both this file and CLAUDE.md. If they ever drift, CLAUDE.md wins.
Cross-edit obligation
- Change
CLAUDE.md→ also update this file in the same commit. - A
scripts/sync-agents-md.shscript (added in v0.2) will enforce this with a pre-commit hook.
Mandatory reading order at session start
CLAUDE.md— operating manualDECISIONS.md— architectural decisions you cannot violatePROGRESS.md— current state and next stepsgit log --oneline -10
Mandatory action at session end
- Append a dated entry to
PROGRESS.md. - If a non-trivial decision was made, append a
DEC-NNNentry toDECISIONS.md. - Conventional-commit message (
feat:,fix:,chore:,docs:,test:,refactor:). - Never push without explicit user instruction.
(For the full operating manual, see CLAUDE.md.)
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.
- 3d ago First seen · 26 lines · 328 tokens per session scan A 76014aa56d83
forensic-deepdive AGENTS.md is an instructions file published in the GitHub repository Dhevenddra/forensic-deepdive (2 stars, last pushed 18d ago), licensed Apache-2.0. It adds 328 tokens to every session, about $0.0016 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 instructions, from other repositories
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
navegador CLAUDE.md
Instructions for ConflictHQ/navegador, covering navegador — claude context, what it is, stack, package layout and falkordb connection.
ChatCrystal AGENTS.md
Instructions for ZengLiangYi/ChatCrystal, covering agents.md, project overview, commands, development (server port 3721 + client port 13721) and build for production.
engram CLAUDE.md
Instructions for NickCirv/engram, covering codebase structure (auto-generated by engram), core entities, structure and key dependencies.
superlocalmemory AGENTS.md
AGENTS.md instructions for qualixar/superlocalmemory, covering gitnexus — code intelligence, always do, never do, resources and cli.
superlocalmemory copilot-instructions.md
Copilot instructions for qualixar/superlocalmemory, covering superlocalmemory (slm) — agent rules, session start, remember, recall and optimize (fail-open).