What is chat-analyzer?

A tool for analyzing exported SpecStory chat histories from coding-agent sessions. It reports interaction problems such as exposed secrets, repeated restarts, or instructions that caused the work to drift.

Use it to review what went wrong in agent sessions, inspect session statistics and tool use, and improve repository instructions.

It turns a long record of agent conversations into specific problems and suggested improvements for instruction files such as AGENTS.md or CLAUDE.md.

chat-analyzer — Skill for Claude Code and Codex by cyberelf

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 cyberelf/agent_skills --skill spec-story-chat-analyzer

Clone the repo

git clone --depth 1 https://github.com/cyberelf/agent_skills

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/cyberelf/agent_skills/spec-story-chat-analyzer/github.svg)](https://agentmods.dev/skills/cyberelf/agent_skills/spec-story-chat-analyzer)

Your own site

<a href="https://agentmods.dev/skills/cyberelf/agent_skills/spec-story-chat-analyzer"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/spec-story-chat-analyzer/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/cyberelf/agent_skills/spec-story-chat-analyzer"><img src="https://agentmods.dev/badge/skills/cyberelf/agent_skills/spec-story-chat-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,010 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	$0.00070	$0.02010
Opus 5.5	$0.00028	$0.00804
Sonnet 5.5	$0.00014	$0.00402
Haiku 4.5	$0.00007	$0.00201

Measured 2mo ago against content hash 604f5bd777fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chat-analyzer 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (chat_analyze.py), 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/spec-story-chat-analyzer/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chat Analyzer

Analyze SpecStory chat history exports and produce a detailed analysis report with actionable fixes for agent constitution files (AGENTS.md, CLAUDE.md, etc.).

Quick Start

# Get full analysis report (main output)
python3 chat_analyze.py analyze data/history.md

# Get problems checklist
python3 chat_analyze.py problems data/history.md

# Supporting commands for deep-dive
python3 chat_analyze.py stats   data/history.md
python3 chat_analyze.py toc     data/history.md
python3 chat_analyze.py tools   data/history.md
python3 chat_analyze.py show    data/history.md <LINE>
python3 chat_analyze.py grep    data/history.md "<pattern>"

Output Format

The analyze command produces a comprehensive report:

# Chat History Analysis: [filename]

## Summary
- Sessions: N
- Messages: N
- Tool calls: N
- Estimated tokens: Nk
- Dominant tool mix: tool1 N, tool2 N, tool3 N
- High-risk indicators: secret exposure, scope drift, restart loops

## Primary Findings

### 1. Secret Exposure In Chat
Severity: high
Evidence: [specific line numbers with credentials]
Pattern: [what went wrong]
Impact: [consequences]
Recommended fix: [concrete actions]

### 2. Scope Drift Across Major Sessions
...

### 3. Environment Churn And Restart Loops
...

## Session-By-Session Breakdown

### Session at line N: [title]
- Shape: N messages, N tool calls.
- Issue: [problems detected]
- Pattern: [behavioral pattern]
- Better split: [recommendation]

## Recommended Conversation Policy Changes
1. [Specific policy recommendation]
2. [Specific policy recommendation]
...

Problem Detection

The analyzer detects these high-value patterns:

Critical Issues (High Severity)

Pattern	Detection	Impact
Secret exposure	Database URLs, API keys, passwords, tokens in chat	Credentials compromised, export file becomes sensitive
Scope drift	Session topic changes significantly from original request	Acceptance criteria unclear, test results unreliable
Infrastructure failure	API errors, model config errors, network failures	Sessions blocked entirely, no deliverable output

Read the full file on GitHub · 273 lines

Files

What ships with it

1 file 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.

chat_analyze.py 53 KB runs code

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.

2mo ago First seen · 273 lines · 70 tokens per session scan A 604f5bd777fc

Subscribe to this mod's changes

chat-analyzer is a skill published in the GitHub repository cyberelf/agent_skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 2,010 once invoked, about $0.0003 per session on Opus 5.5. 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.

Analytics and metrics

chat-analyzer next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chat-analyzercyberelf/agent_skills	Skill	2	2mo ago	MIT	A	70	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex