analyze-session

analyze-session is a skill for Claude Code from Temikus/claude-watchdog. It costs 10 tokens per session (1,045 once invoked), scanned A, original, Apache-2.0.

A critical review of the current Claude Code conversation, including the requested work, repository changes, and recent commits.

In plain words
What is it for?
Use it to inspect goals, changed files, instruction compliance, and unfinished or incorrect work in a coding session.
Why use it?
It helps reveal whether the task was actually completed and whether the changes match what was requested.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the claude-watchdog plugin — 1 skill, 1 agent, 4 hooks shipped together

Good fit Use it to inspect goals, changed files, instruction compliance, and unfinished or incorrect work in a coding session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/temikus/claude-watchdog/analyze-session
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 Temikus/claude-watchdog --skill analyze-session
Clone the repo
git clone --depth 1 https://github.com/Temikus/claude-watchdog

Made for: Claude Code.

Or install claude-watchdog, the plugin that ships this one along with the rest of its 1 skill, 1 agent, 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.

agentmods badge for analyze-session

README.md
[![agentmods](https://agentmods.dev/badge/skills/temikus/claude-watchdog/analyze-session.svg)](https://agentmods.dev/skills/temikus/claude-watchdog/analyze-session)
Your own site
<a href="https://agentmods.dev/skills/temikus/claude-watchdog/analyze-session"><img src="https://agentmods.dev/badge/skills/temikus/claude-watchdog/analyze-session.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,045 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.01045
Opus 5 $0.00005 $0.00522
Sonnet 5 $0.00002 $0.00209
Haiku 4.5 $0.00001 $0.00104

Measured today against content hash ecc85d4a6656, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

analyze-session 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 today.

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/analyze-session/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a critical session analyst reviewing the current Claude Code session.

This is the on-demand twin of agents/session-analyzer.md. The rubric below is kept in step with that agent so both produce the same shape of review. The one deliberate difference: this skill reads the live conversation rather than a condensed transcript file, so it carries no transcript legend and no slice framing - there is no delta, no touched-file list, and no previous analysis to avoid repeating.

Bash is read-only

allowed-tools cannot scope Bash to a command pattern - it grants the whole tool. Treat it as read-only: git inspection and file inspection only (git diff, git log, git status, git show, cat, ls, grep, find, head, tail). git show is expected constantly - most work is already committed by the time this runs. Never run builds, tests, linters, or any command that changes repo or filesystem state.

Workflow

  1. Read the conversation so far to understand what was asked and attempted.
  2. If the project has instruction files (CLAUDE.md, .claude/rules/*.md, project first, then ~/.claude), read them. They are the reference for Compliance.
  3. Run git diff --stat and git diff --cached --stat, then read full hunks for the files the session actually touched: git diff -- <paths>. Changes in files the session never touched are pre-existing working-tree state and MUST NOT be attributed to it.
  4. Run git log --oneline -5.
  5. Cross-reference the asks against the diff.

Output

Your final message MUST begin with ### Goals - no preamble, no "Confirmed:", no summary of what you checked or read first. The first characters you emit are ### Goals.

### Goals (mandatory, 2-4 sentences): were the user's asks achieved, cross-checked against the diff.

Fast path: no findings clear the signal threshold below -> Goals, then ### Recommendations with none, stop. Do not open a section to write that it found nothing.

Signal threshold: a finding must have caused a wrong result, wasted a meaningful amount of work, broke an instruction, or would recur. Do not report style nits, hypothetical risks, things the user can already see in the diff, or anything you would not interrupt a colleague for. Not recommending anything is the expected outcome for a normal session, not a failure to analyse.

Read the full file on GitHub · 56 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. today Changed · +7 lines ecc85d4a6656
  2. 8d ago First seen · 49 lines · 10 tokens per session scan A 4581c3dbacf0

Subscribe to this mod's changes

analyze-session is a skill published in the GitHub repository Temikus/claude-watchdog (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 10 tokens to every session and 1,045 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens