Home / techwolf-ai / ai-first-toolkit · plugins/session-tools/skills/session-search/SKILL.md · GitHub

session-search skillA

session-search is agent-read markdown (skill) from techwolf-ai/ai-first-toolkit: Find context from past Claude Code (CLI) and Claude Cowork (desktop) sessions on this Mac. Use when the user wants to recall something they did before but can't find it , phrasings like "where did I work on X", "find that session where I…", "when did I last do Y", "pull up the conversation about Z", "that time I built/tried/discussed …". Searches by kind (code/cowork), time range, title, working directory, or free-text content across all transcripts..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# session-search

> **Platforms: Claude Code / Cowork and Codex.** `find_sessions.py` and `show_session.py` detect the host (via the `platform` stamp `install.sh` writes, or `AI_FIRST_PLATFORM`) and route to the right store: Claude Code (`~/.claude/projects`) + Cowork transcripts, or Codex rollouts (`~/.codex/sessions/**/rollout-*.jsonl`). Both support list, time/cwd/title filters, and full-text `--grep`. **Antigravity is not supported**: its IDE conversations are AEAD-encrypted at rest (`~/.gemini/antigravity/conversations/*.pb`) and its unencrypted CLI store carries no parseable turn content, so the skill prints a clear "not available" message and exits.

Two scripts in `scripts/` locate past sessions and dump their content:

- `find_sessions.py` , discover + filter sessions (metadata + optional full-text grep).
- `show_session.py` , print a single session's conversation (user/assistant turns) in readable form.

Both read directly from disk , no API calls, no auth. They resolve paths from `$HOME` so they work for any macOS user:

- Claude Code CLI: `~/.claude/projects/*/\*.jsonl`
…

Read the whole file at its exact version.

How to install

Latest version
mdr add techwolf-ai/ai-first-toolkit/session-search@git:20260629.46e9161
Exact content
mdr add techwolf-ai/ai-first-toolkit/session-search@sha256:ce0c7b121b2f5aac

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_d6nib5atj4b6ihp7.svg)](https://markdownregistry.com/a/art_d6nib5atj4b6ihp7)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260629.46e9161 latest2026-06-29 46e9161 4,265 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4265 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

techwolf-ai/ai-first-toolkit · 100 stars · license MIT · pushed 2026-09-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_d6nib5atj4b6ihp7
GET https://markdownregistry.com/api/v1/resolve?ref=techwolf-ai/ai-first-toolkit/session-search
GET https://markdownregistry.com/api/v1/blob/ce0c7b121b2f5aac8e8ee925869bc5b8643e40c7d927603a7b9b3478441b63aa

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from techwolf-ai/ai-first-toolkit

AGENTS.md agents
techwolf-ai/ai-first-toolkit · AGENTS.md
git:20260922.e58574c · audit A · 100 stars
task-profile skill
techwolf-ai/ai-first-toolkit · plugins/ai-adoption/skills/task-profile/SKILL.md · Mine the user's Claude Code + Cowork session history into a structured task profile, what they do with AI, how often…
git:20260916.a134489 · audit A · 100 stars
token-doctor skill
techwolf-ai/ai-first-toolkit · plugins/ai-adoption/skills/token-doctor/SKILL.md · Personal diagnosis of where your Claude Code + Cowork spend goes. Reads local transcripts, prints your conversation…
git:20260916.a134489 · audit A · 100 stars
AGENTS.md@plugins/ai-firstify/codex agents
techwolf-ai/ai-first-toolkit · plugins/ai-firstify/codex/AGENTS.md
git:20260310.f8426c2 · audit A · 100 stars
ai-firstify skill
techwolf-ai/ai-first-toolkit · plugins/ai-firstify/skills/ai-firstify/SKILL.md · Analyze, re-engineer, or bootstrap projects to align with AI-first design principles. Use when asked to review, audit…
git:20260410.852272e · audit A · 100 stars
AGENTS.md@plugins/content-studio/codex agents
techwolf-ai/ai-first-toolkit · plugins/content-studio/codex/AGENTS.md
git:20260310.f8426c2 · audit A · 100 stars
analyze-performance skill
techwolf-ai/ai-first-toolkit · plugins/content-studio/skills/analyze-performance/SKILL.md · Analyze engagement patterns across published posts to identify what works. Use when asked to review performance, find…
git:20260305.f09c96a · audit A · 100 stars
brainstorm-linkedin skill
techwolf-ai/ai-first-toolkit · plugins/content-studio/skills/brainstorm-linkedin/SKILL.md · Generate LinkedIn post ideas from external sources (files, URLs, research). Use when the user provides source material…
git:20260305.f09c96a · audit A · 100 stars
brainstorm-opinion skill
techwolf-ai/ai-first-toolkit · plugins/content-studio/skills/brainstorm-opinion/SKILL.md · Generate opinion piece ideas from recent LinkedIn posts (last 30 days). Use when asked to find opinion topics…
git:20260305.f09c96a · audit A · 100 stars
content-studio skill
techwolf-ai/ai-first-toolkit · plugins/content-studio/skills/content-studio/SKILL.md · Entry point for the TechWolf content-studio plugin. Use to understand the workflow, pick the right content skill, or…
git:20260310.f8426c2 · audit A · 100 stars
setup-content-studio skill
techwolf-ai/ai-first-toolkit · plugins/content-studio/skills/setup-content-studio/SKILL.md · Set up a new content studio for a person. Copies the plugin template, adapts it to the person's voice, themes, and…
git:20260610.38aa811 · audit A · 100 stars
write-blog-post skill
techwolf-ai/ai-first-toolkit · plugins/content-studio/skills/write-blog-post/SKILL.md · Write or develop a blog post. Use for blog content - writing, drafting, developing ideas into drafts, or editing…
git:20260306.4818d5d · audit A · 100 stars

Every file in techwolf-ai/ai-first-toolkit

Other files named session-search

session-search skill
ar9av/obsidian-wiki · .skills/session-search/SKILL.md · Find a past agent session by topic and load its context into the current conversation. Searches the session-brain topic…
git:20260730.4bf87a8 · audit A · 3,474 stars
session-search skill
hoangsonww/claude-code-agent-monitor · plugins/ccam-sessions/skills/session-search/SKILL.md · Find Claude Code sessions tracked by the Agent Monitor by project (cwd), model, status, or date, then rank the matches…
git:20260804.9eab0d7 · audit A · 1,014 stars

Browse by kind, by grade A, or by owner.