claude-dejavu AGENTS.md

Project instructions for claude-dejavu, a Rust and TypeScript monorepo—a single repository containing several related programs and libraries. The project reads coding-session logs, detects repeated patterns, and applies rules to a CLAUDE.md file.

In plain words
What is it for?
Use them when adding features, fixing bugs, writing tests, or reviewing architecture across the Rust library, command-line tool, and TypeScript launcher.
Why use it?
They explain the project structure, coding conventions, and how its parts fit together before an agent changes the code.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/cmg8431/claude-dejavu/agents-md
Clone the repo
git clone --depth 1 https://github.com/cmg8431/claude-dejavu

Made for: Codex, OpenCode.

Per session 589 This file is loaded in full into every session.
When invoked 589 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00589 $0.00589
Opus 5 $0.00295 $0.00295
Sonnet 5 $0.00118 $0.00118
Haiku 4.5 $0.00059 $0.00059

Measured yesterday against content hash af61766f559f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-dejavu AGENTS.md scanned grade A with 1 finding 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **TypeScript launcher** (`packages/cli/`) — platform detection + `spawnSync` execution
AGENTS.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Guidelines

Commit Message Convention

<type>(<scope>): <description>

Types

Type Description
feat New feature
fix Bug fix
refactor Code refactoring (no behavior change)
docs Documentation only
test Adding or updating tests
chore Maintenance tasks
perf Performance improvements

Architecture Overview

claude-dejavu is a Rust + TypeScript hybrid monorepo (same pattern as codagotchi):

  • Rust library (crates/dejavu-core/) — JSONL parser, detectors, DB, rule engine
  • Rust binary (crates/dejavu-cli/) — CLI with subcommands (init, scan, list, stats)
  • TypeScript launcher (packages/cli/) — platform detection + spawnSync execution

Core Loop

Session logs (.jsonl) → Parser → Detectors → Patterns (SQLite) → Rules → CLAUDE.md patch
                                                                            │
                          Rule effectiveness scoring ◀──────────────────────┘

Detectors (v0)

  1. Revert Cycle — Edit → revert → re-edit on same file
  2. Repeated Error — Same error appears across sessions, same fix each time
  3. Silent Fix — User silently corrects Claude's output without asking

Key Design Decisions

  • SQLite with WAL mode. ~/.local/share/claude-dejavu/dejavu.db
  • CLAUDE.md metadata in HTML comments. Claude ignores them, dejavu reads/writes them.
  • No traits for detectors. Each detector is a standalone detect(&[ParsedSession]) function.
  • anyhow::Result for all fallible functions.

Adding a New Detector

  1. Create detector/{name}.rs with pub fn detect(sessions: &[ParsedSession]) -> Vec<Detection>
  2. Add pub mod {name}; to detector/mod.rs
  3. Add call in run_all_detectors()

Adding a New CLI Command

  1. Create commands/{name}.rs with pub fn run(...) -> Result<()>
  2. Add pub mod {name}; to commands/mod.rs
  3. Add variant to Commands enum in main.rs
  4. Add match arm in main()

Read the full file on GitHub · 69 lines

Changes

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.

  1. yesterday First seen · 69 lines · 589 tokens per session scan A af61766f559f

Subscribe to this mod's changes

claude-dejavu AGENTS.md is an instructions file published in the GitHub repository cmg8431/claude-dejavu (2 stars, last pushed 3mo ago), licensed MIT. It adds 589 tokens to every session, about $0.0029 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

claude-mem CLAUDE.md

Instructions for thedotmack/claude-mem, covering claude-mem: ai development instructions, build, file locations, requirements and documentation.

thedotmack/claude-mem · 271 tokens

claude-mem copilot-instructions.md

Instructions for thedotmack/claude-mem, a project described as: Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot…

thedotmack/claude-mem · 54 tokens

vexic AGENTS.md

Instructions for PyroDonkey/vexic, covering vexic agent instructions, project, architecture boundaries, package boundary and host ports.

PyroDonkey/vexic · 5,319 tokens

longhand CLAUDE.md

Instructions for Wynelson94/longhand, covering longhand mcp tools — efficient usage guide, quick decision tree, anti-patterns (avoid), tool pairing patterns and pattern b: recall past work across sessions (1-2 calls).

Wynelson94/longhand · 1,006 tokens

claude-mem-sync CLAUDE.md

Instructions for lopadova/claude-mem-sync, covering claude.md — claude-mem-sync, what this project is, architecture, project structure and commands.

lopadova/claude-mem-sync · 2,871 tokens

junto-memory CLAUDE.md

Instructions for tlemmons/junto-memory, covering junto memory (mcp server), claude identity (required — do this first), project roster (post-cutover 2026-05-07), rename aliases (active 30 days from 2026-05-07) and key files.

tlemmons/junto-memory · 3,134 tokens