What is dejavu-report?

A weekly review of patterns that a coding assistant has learned from past mistakes, including which rules worked and which may be outdated.

Use it to review newly detected patterns, recently triggered rules, inactive rules, confidence levels, and overall rule grades for the past week.

It shows whether the learned rules are preventing repeated mistakes or adding unnecessary clutter. It removes the need to inspect rule statistics manually.

dejavu-report — 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 weekly-report

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/weekly-report/github.svg)](https://agentmods.dev/skills/cmg8431/claude-dejavu/weekly-report)

Your own site

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

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 444 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	$0.00037	$0.00444
Opus 5	$0.00018	$0.00222
Sonnet 5	$0.00007	$0.00089
Haiku 4.5	$0.00004	$0.00044

Measured 12d ago against content hash 80e3e6b3a5ea, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dejavu-report 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 12d 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/weekly-report/SKILL.md · 65 lines

What it actually says

claude-dejavu: Weekly Report

You are generating a weekly effectiveness report for claude-dejavu.

Steps

First, gather statistics:

claude-dejavu stats --path "$(pwd)"

Then list all rules with their grades:

claude-dejavu list --path "$(pwd)"

Format a report with the following sections:

New Patterns This Week

List any rules created in the last 7 days. If stats show no new rules, say "No new patterns detected this week."

Rules That Fired (Prevented Mistakes)

Highlight rules with fire_count > 0 that have fired recently. These are the rules that actively prevented Claude from repeating past mistakes. Show each rule's grade badge and fire count.

Dead Rules to Consider Removing

List rules with status "dead" or rules that have not fired in 14+ days with low confidence (< 0.6). Suggest the user remove these to keep the rule set lean.

Effectiveness Trend

Summarize overall health:

Total active rules
Average confidence across active rules
Total fires this period
Grade distribution (how many A/B/C/D rules)

Present the report in a clean, readable format:

=== claude-dejavu Weekly Report ===

New patterns:     2 discovered
Rules fired:      5 times (prevented 5 mistakes)
Dead rules:       1 candidate for removal
Overall health:   Good (avg confidence: 0.82)

Grade distribution: A:3  B:2  C:1  D:0

Important

Be concise but informative
Highlight wins (rules that fired = mistakes prevented)
If there are no rules yet, encourage the user to run more sessions so dejavu can learn
If effectiveness is declining (many dead rules, low confidence), suggest running a fresh scan

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.

12d ago First seen · 65 lines · 37 tokens per session scan A 80e3e6b3a5ea

Subscribe to this mod's changes

dejavu-report is a skill published in the GitHub repository cmg8431/claude-dejavu (2 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 444 once invoked, about $0.0002 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-report