SessionSearch

SessionSearch is a skill for Claude Code from CarbeneAI/Forge. It costs 53 tokens per session (1,060 once invoked), scanned A, original, MIT.

A search tool for past coding-agent sessions, including conversation logs, tool use, and spending records.

In plain words
What is it for?
Use it to find earlier sessions, review activity over time, measure tool usage, or check session costs.
Why use it?
It saves you from manually scanning old session files when you need to remember previous work or investigate usage.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: mentions subagents.

Good fit Use it to find earlier sessions, review activity over time, measure tool usage, or check session costs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/carbeneai/forge/sessionsearch
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 CarbeneAI/Forge --skill sessionsearch
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code.

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 SessionSearch

README.md
[![agentmods](https://agentmods.dev/badge/skills/carbeneai/forge/sessionsearch/github.svg)](https://agentmods.dev/skills/carbeneai/forge/sessionsearch)
Your own site
<a href="https://agentmods.dev/skills/carbeneai/forge/sessionsearch"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/sessionsearch/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.

agentmods 80×15 button for SessionSearch

Your own site · 80×15
<a href="https://agentmods.dev/skills/carbeneai/forge/sessionsearch"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/sessionsearch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,060 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 $0.00053 $0.01060
Opus 5 $0.00026 $0.00530
Sonnet 5 $0.00011 $0.00212
Haiku 4.5 $0.00005 $0.00106

Measured 7d ago against content hash 483b7b5be9de, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

SessionSearch 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 7d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (tools/CostAnalyzer.ts, tools/SessionSearch.ts, tools/ToolStats.ts), 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.

.claude/skills/SessionSearch/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SessionSearch

Search and analyze PAI session history, including events, tool usage, and costs.

Workflow Routing

When executing a workflow, call the notification script via Bash:

${PAI_DIR}/tools/skill-workflow-notification WorkflowName SessionSearch
Workflow Trigger File
Search "search history", "find sessions", "what did I work on" workflows/Search.md
AnalyzeCost "cost tracking", "token usage", "how much did I spend" workflows/AnalyzeCost.md
ToolUsage "tool stats", "which tools", "tool usage" workflows/ToolUsage.md
Timeline "session timeline", "activity over time", "when did I" workflows/Timeline.md

Examples

Example 1: Search for past work

User: "What did I work on related to Discord?"
→ Invokes Search workflow
→ Searches all-events.jsonl files for "discord" keyword
→ Returns matching sessions with timestamps and context

Example 2: Analyze tool usage

User: "Which tools do I use most often?"
→ Invokes ToolUsage workflow
→ Aggregates tool_name from events
→ Returns ranked list: Bash (45%), Read (25%), Edit (15%)...

Example 3: Check session costs

User: "How much have I spent on PAI this month?"
→ Invokes AnalyzeCost workflow
→ Parses token counts from session data
→ Returns daily/weekly/monthly breakdown

Data Sources

Event Logs (JSONL)

Location: ${PAI_DIR}/history/raw-outputs/YYYY-MM/YYYY-MM-DD_all-events.jsonl

Event Types:

  • SessionStart - New session began
  • SessionEnd - Session completed
  • UserPromptSubmit - User input
  • PreToolUse / PostToolUse - Tool execution
  • SubagentStop - Subagent completed
  • Stop - Session stopped

Event Fields:

{
  "source_app": "pai",
  "session_id": "uuid",
  "hook_event_type": "PostToolUse",
  "payload": {
    "session_id": "uuid",
    "transcript_path": "/path/to/transcript.jsonl",
    "cwd": "/working/directory",
    "tool_name": "Bash",
    "tool_input": {...},
    "tool_response": {...}
  },
  "timestamp": 1767503279676,
  "timestamp_pst": "2026-01-03 21:07:59 PST"
}

Read the full file on GitHub · 145 lines

Files

What ships with it

8 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.

  1. 7d ago First seen · 145 lines · 53 tokens per session scan A 483b7b5be9de

Subscribe to this mod's changes

SessionSearch is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,060 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

knowledge-management

../../../governance/knowledge-management/SKILL.md.

jaskaranhundal/usap-skills · 0 tokens

analyzing-memory-forensics-with-lime-and-volatility

Performs Linux memory acquisition using LiME (Linux Memory Extractor) kernel module and analysis with Volatility 3 framework. Extracts process lists, network connections, bash history, loaded kernel modules, and injected code from Linux memory images. Use when performing incident response on compromised Linux systems.

mukul975/Anthropic-Cybersecurity-Skills · 71 tokens

wiki-retrieve

Build and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta…

AgriciDaniel/claude-obsidian · 81 tokens

obsidian-bases

Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.

AgriciDaniel/claude-obsidian · 69 tokens

commonly

You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…

Team-Commonly/commonly · 0 tokens

daily-briefing

Proactive daily briefing that fires on a recurring schedule, pulls recent memory and workspace context, composes a structured summary (action items, progress, radar, next steps), and delivers it to all active channels. Enable with a time like "set up my daily briefing at 9am". Disable, reschedule, or check status at…

vellum-ai/vellum-assistant · 75 tokens