Agent skill

Session Reader

by HazAT in HazAT/pi-config

Efficiently read and analyze pi agent session JSONL files. An agent skill from HazAT/pi-config.

MITAuto-check passedDevelopment

Install Session Reader

skills CLI
$ npx skills add HazAT/pi-config --skill session-reader -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HazAT/pi-config session-reader --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HazAT/pi-config.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/session-reader .claude/skills/session-reader && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
session-reader
GitHub stars
451
Token cost
~808 tokens
SKILL.md length
284 words
Files
3 (incl. scripts, references)
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Efficiently read and analyze pi agent session JSONL files. An agent skill from HazAT/pi-config.

  • Works in 4 steps: Find the Session → Start with Table of Contents → Read the Conversation → …
  • Asked to read a session
  • SKILL.md covers Step 1: Find the Session, Step 2: Start with Table of…, Step 3: Read the Conversation and Step 4: Drill Into a Turn, plus 5 more sections
  • Runs Python scripts from its folder; calls uv

What it does

Session Reader is an agent skill from HazAT/pi-config. Efficiently read and analyze pi agent session JSONL files. Use when asked to "read a session", "review a session", "analyze a session", "what happened in this session", "load session", "parse session", "session history", "go through sessions", or given a .jsonl session file path.

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/session-format.md` and `scripts/read_session.py`).

It sits in Development. The repository describes itself as: My personal pi coding agent configuration - skills and extensions. The licence is MIT.

When your agent uses it

  • Asked to read a session
  • Review a session
  • Analyze a session
  • What happened in this session

Example prompts

  • “read a session”
  • “review a session”
  • “analyze a session”
  • “/session-reader”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Find the Session
  2. Start with Table of Contents
  3. Read the Conversation
  4. Drill Into a Turn

What it can do on your machine

Read from SKILL.md and the folder at commit 655acd4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • uv

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Session Reader loads about 808 tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 74 tokens; SKILL.md has 284 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~808
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from HazAT/pi-config at commit 655acd4, republished under its MIT licence (© HazAT). 284 words, ~808 tokens.

Download SKILL.mdSave it as .claude/skills/session-reader/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
session-reader
description
Efficiently read and analyze pi agent session JSONL files. Use when asked to "read a session", "review a session", "analyze a session", "what happened in this session", "load session", "parse session", "session history", "go through sessions", or given a .jsonl session file path.

Read Pi Sessions

Parse pi session JSONL files into readable output. Sessions live in ~/.pi/agent/sessions/<project>/ as .jsonl files.

Step 1: Find the Session

bash
ls -t ~/.pi/agent/sessions/*<project>*/*.jsonl | head -10

Step 2: Start with Table of Contents

Always start with toc to get a numbered map of the session:

bash
uv run ${CLAUDE_SKILL_ROOT}/scripts/read_session.py <path> --mode toc

This prints a compact numbered list of every user exchange with timestamps and tools used.

Step 3: Read the Conversation

Default mode — shows only user messages and assistant text responses. Tool calls are hidden but hinted at with [used: tool1, tool2].

bash
# Full conversation (default mode)
uv run ${CLAUDE_SKILL_ROOT}/scripts/read_session.py <path>

# Specific range
uv run ${CLAUDE_SKILL_ROOT}/scripts/read_session.py <path> --offset 5 --limit 3

# Search for specific topic
uv run ${CLAUDE_SKILL_ROOT}/scripts/read_session.py <path> --search "error"

Step 4: Drill Into a Turn

See everything about a specific exchange — thinking, tool calls, tool results, costs:

bash
uv run ${CLAUDE_SKILL_ROOT}/scripts/read_session.py <path> --mode turn --turn 7

Mode Reference

ModeShowsUse for
conversationUser + assistant text only (default)Reading what happened
tocNumbered exchange listNavigation, finding the right turn
turnFull detail for one exchangeDrilling into specifics
issuesErrors, failures, retries, user complaintsFinding what broke
overviewMetadata + exchange summariesQuick session assessment
fullEverything including tool I/ODeep debugging
toolsTool calls and results onlyUnderstanding agent actions
costsToken usage and cost per turnCost analysis
subagentsSubagent task/status/cost/pathsReviewing delegated work

Flags

FlagEffect
--offset NSkip first N exchanges
--limit NShow at most N exchanges
--turn NExchange number to drill into (with --mode turn)
--search TERMFilter exchanges containing TERM (case-insensitive)
--max-content NMax chars per block (default: 3000, 0=unlimited)

Typical Workflow

  1. --mode toc → scan the session, find interesting exchanges
  2. Default (conversation) → read the human-readable flow
  3. --mode turn --turn N → drill into specific exchanges
  4. --mode subagents → review delegated work and follow subagent session paths

Subagent Drill-Down

Subagent session files can be read with the same script:

bash
# From --mode subagents output, grab the JSONL path
uv run ${CLAUDE_SKILL_ROOT}/scripts/read_session.py <subagent-jsonl-path> --mode toc

Session Format Reference

Read ${CLAUDE_SKILL_ROOT}/references/session-format.md only if custom parsing is needed.

© HazAT, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (scripts, references) in skills/session-reader of HazAT/pi-config.

  • SKILL.md
  • references/session-format.md
  • scripts/read_session.py

Open the folder on GitHubat commit 655acd4

Compare with similar skills

Session Reader next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Session Reader compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Session Reader this skillHazAT/pi-config451—~808Automated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from HazAT/pi-config

All 10 skills in this repo
  • Defines the local standard for standalone Pi extension repositories.

    451 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Superconductor

    HazAT/pi-config

    Operates the super.engineering/Superconductor sc CLI for app-managed agents, teams, sessions, layouts, worktrees, and review threads.

    451 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed
  • Plan

    HazAT/pi-config

    Interactively investigate a request, compare approaches, and write the selected implementation plan to a supplied Markdown path.

    451 GitHub stars~528 tokensUpdated 1 mo ago
    Auto-check passed
  • Review

    HazAT/pi-config

    Coordinate a model-diverse local code review, automatically repair actionable findings with sequential workers, and re-review to a final verdict.

    451 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Configures a repository for super.engineering with repo-owned worktree setup and development-server scripts.

    451 GitHub stars~999 tokensUpdated 1 mo ago
    Auto-check passed
  • Worker

    HazAT/pi-config

    Implement one todo or review-fix task supplied by a coordinator, verify it, create one focused commit, and report evidence through the current Superconductor session.

    451 GitHub stars~679 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Session Reader

What does Session Reader do?

Efficiently read and analyze pi agent session JSONL files. An agent skill from HazAT/pi-config. Session Reader is an agent skill from HazAT/pi-config. Efficiently read and analyze pi agent session JSONL files.

When should I use Session Reader?

Session Reader fits situations like: asked to read a session; review a session; analyze a session; what happened in this session.

How do I install Session Reader in Claude Code?

Run `npx skills add HazAT/pi-config --skill session-reader -a claude-code`. Or copy the skill folder (skills/session-reader in HazAT/pi-config) into .claude/skills/session-reader in your project. Claude Code loads it when a task matches its description.

How do I install Session Reader in Codex?

Run `npx skills add HazAT/pi-config --skill session-reader -a codex`. Or copy the skill folder (skills/session-reader in HazAT/pi-config) into .agents/skills/session-reader in your project. Codex loads it when a task matches its description.

Can I use Session Reader in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HazAT/pi-config --skill session-reader -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/session-reader, .gemini/skills/session-reader, .github/skills/session-reader and .opencode/skills/session-reader in your project.

What does Session Reader need to run?

Going by SKILL.md and its folder, Session Reader needs Python for the scripts in its folder and the command-line tools its instructions call (uv). Our summary lists: Python 3.

Does Session Reader access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Session Reader safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Session Reader use?

Session Reader is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Session Reader use?

About 808 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.4k tokens, read only when the agent opens those files.

What are the alternatives to Session Reader?

Skills that share tags, products or a category with Session Reader: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Session Reader?

HazAT (a GitHub user) maintains it in HazAT/pi-config, which has 451 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on August 25, 2026.

Source: HazAT/pi-config on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.