What is dejavu-rules?

A conversation-based manager for rules stored in CLAUDE.md, a project file that tells the coding assistant how to work. It can add, edit, remove, and review those rules.

Use it to remember preferences, change existing instructions, remove rules, or review rule fire counts, grades, and inactive entries.

It lets you maintain project instructions in ordinary language instead of editing the file or running commands yourself. Feedback shows which rules are useful or dormant.

dejavu-rules — Skill for Claude Code by cmg8431

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.

Any agent

npx skills add cmg8431/claude-dejavu --skill dejavu-rules

Clone the repo

git clone --depth 1 https://github.com/cmg8431/claude-dejavu

Made for: Claude Code.

Or install claude-dejavu, the plugin that ships this one along with the rest of its 6 skills, 4 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cmg8431/claude-dejavu/dejavu-rules/github.svg)](https://agentmods.dev/skills/cmg8431/claude-dejavu/dejavu-rules)

Your own site

<a href="https://agentmods.dev/skills/cmg8431/claude-dejavu/dejavu-rules"><img src="https://agentmods.dev/badge/skills/cmg8431/claude-dejavu/dejavu-rules/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cmg8431/claude-dejavu/dejavu-rules"><img src="https://agentmods.dev/badge/skills/cmg8431/claude-dejavu/dejavu-rules.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 433 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.00433
Opus 5	$0.00028	$0.00217
Sonnet 5	$0.00011	$0.00087
Haiku 4.5	$0.00006	$0.00043

Measured 11d ago against content hash ec6de3420655, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dejavu-rules 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 11d 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.

plugin/skills/dejavu-rules/SKILL.md · 61 lines

What it actually says

Manage dejavu Rules

You can help the user manage their claude-dejavu rules through conversation.

Adding Rules

When the user states a preference or rule, use the add_rule MCP tool:

Examples:

"이 프로젝트에서는 pnpm만 써" → add_rule("This project uses pnpm, not npm.")
"항상 테스트 먼저 돌려" → add_rule("Always run tests before committing.")
"Remember to use semantic HTML" → add_rule("Use semantic HTML tags instead of generic divs.")

Or via CLI:

claude-dejavu rules add "This project uses pnpm, not npm."

Editing Rules

When the user wants to modify a rule:

First show current rules using list_rules
Then use edit_rule with the rule ID and new text

claude-dejavu rules edit r-001 "Use pnpm for all package operations, including scripts."

Removing Rules

claude-dejavu rules remove r-001

Reviewing Rules with Feedback

Show the user which rules are working and which aren't:

claude-dejavu rules feedback

This shows:

Fire count per rule (how many times it prevented a mistake)
Quality grade (A/B/C/D)
Dormant rules that might need removal

Guidelines

When adding rules, write them as clear, actionable instructions
Translate user's natural language into concise rule text
If the user speaks Korean/Japanese, still write the rule in English (Claude reads CLAUDE.md in English)
After adding/editing, confirm what was done and show the rule ID
Suggest reviewing with /dejavu or rules feedback periodically

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.

11d ago First seen · 61 lines · 56 tokens per session scan A ec6de3420655

Subscribe to this mod's changes

dejavu-rules is a skill published in the GitHub repository cmg8431/claude-dejavu (2 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 433 once invoked, about $0.0003 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.

Memory and context ai ai-agents ai-memory anthropic artificial-intelligence chromadb

ccs-align

Run the CCS Align seat's hourly breathing cycle — prove the local claude-mem worker is healthy, pull needle observations through search → timeline → getobservations, land them in a seat-owned middle cache via atomic grab → append → filter exclude-marks → replace, manage exclude marks, and walk house → project → seat…

thedotmack/claude-mem · 136 tokens

weekly-digests

Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…

thedotmack/claude-mem · 93 tokens

mode-creator

Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and startup-context verification. Use this whenever someone asks to customize what claude-mem remembers, create or change a mode…

thedotmack/claude-mem · 94 tokens

dejavu-rules