What is meta-analyst?

A self-review tool for coding-agent sessions that records errors, successes, retries, improvements, and lessons. It then produces reports about recurring patterns and inefficient work.

Use it to log session events, review what went wrong or worked, and identify improvements to recurring workflows.

It makes repeated failures and slow parts of an agent workflow visible instead of relying on memory.

meta-analyst — Skill for Claude Code and Codex by JansenAnalytics

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 JansenAnalytics/claudex --skill meta-analyst

Clone the repo

git clone --depth 1 https://github.com/JansenAnalytics/claudex

Made for: Claude Code, Codex.

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/jansenanalytics/claudex/meta-analyst.svg)](https://agentmods.dev/skills/jansenanalytics/claudex/meta-analyst)

Your own site

<a href="https://agentmods.dev/skills/jansenanalytics/claudex/meta-analyst"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/meta-analyst.svg" alt="Measured on agentmods" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 793 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	$0.00024	$0.00793
Opus 5	$0.00012	$0.00396
Sonnet 5	$0.00005	$0.00159
Haiku 4.5	$0.00002	$0.00079

Measured 3d ago against content hash fc33713b6662, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

meta-analyst 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/analyze.cjs, scripts/report.cjs, scripts/track.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/meta-analyst/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta-Analyst

Self-reflection skill that analyzes your session logs, tracks events, and produces efficiency reports. Helps identify what fails often, what takes too long, and what patterns repeat.

Commands

Track an event

node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/meta-analyst/scripts/track.cjs <type> "message" [--category CAT] [--duration DUR] [--source SRC]

Types: error, success, retry, improvement, lesson

Examples:

node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/meta-analyst/scripts/track.cjs error "cloudscraper failed" --category scraping
node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/meta-analyst/scripts/track.cjs success "built kanban skill" --duration 45m --category skill-building
node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/meta-analyst/scripts/track.cjs retry "web_search failed, used searxng" --category search
node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/meta-analyst/scripts/track.cjs lesson "always verify sub-agent output" --category workflow

Generate a report

node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/meta-analyst/scripts/report.cjs [--period week|month|all] [--format markdown|json] [--out-file PATH]

Raw analysis (JSON)

node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/meta-analyst/scripts/analyze.cjs [--period week|month|all]

Data Sources

~/.openclaw-poe/workspace/memory/*.md — daily log files (parsed for tool usage, errors, projects, lessons)
~/.meta-analyst/events.db — SQLite database of tracked events

Report Sections

Tool usage frequency
Error/failure patterns
Common shell commands
Project focus distribution
Sub-agent & retry reliability stats
Tracked events summary
Lessons learned
Auto-generated improvement suggestions

Agent Workflow

During heartbeats (periodic)

Run report.cjs --period week every few days to check trends
Track notable events as they happen (errors, retries, successes)
Review suggestions and act on recurring issues

Read the full file on GitHub · 79 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago First seen · 79 lines · 24 tokens per session scan A fc33713b6662

Subscribe to this mod's changes

meta-analyst is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 793 once invoked, about $0.0001 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 2026-09-03.

Analytics and metrics efficiency-report event-tracking meta patterns self-reflection session-analysis

attack-patterns-reference

Use when classifying a verified web or WordPress behavior and selecting a related validation skill.

uphiago/recon-skills · 23 tokens

agenttrace-session-audit

Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.

sickn33/agentic-awesome-skills · 34 tokens

torchforge-rl-training

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

davila7/claude-code-templates · 49 tokens

regex-mastery

Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.

alibaba/anolisa · 60 tokens

pentest-playbook

7-phase pentest pipeline from passive recon to exploitation.

uphiago/recon-skills · 16 tokens

skill-authoring

Author SKILL.md skills: frontmatter, validator limits, structure.

mateaix/mateclaw · 18 tokens