Borrowing it
Nothing to install: this file belongs to lesleslie/session-buddy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/lesleslie/session-buddy/main/CLAUDE.mdgit clone --depth 1 https://github.com/lesleslie/session-buddyWrote 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.
[](https://agentmods.dev/instructions/lesleslie/session-buddy/claude-md)<a href="https://agentmods.dev/instructions/lesleslie/session-buddy/claude-md"><img src="https://agentmods.dev/badge/instructions/lesleslie/session-buddy/claude-md/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.
<a href="https://agentmods.dev/instructions/lesleslie/session-buddy/claude-md"><img src="https://agentmods.dev/badge/instructions/lesleslie/session-buddy/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.06497 | $0.06497 |
| Opus 5.5 | $0.02599 | $0.02599 |
| Sonnet 5.5 | $0.01299 | $0.01299 |
| Haiku 4.5 | $0.00650 | $0.00650 |
Grade A, and why
session-buddy CLAUDE.md 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 4d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
For a shorter, tool-neutral bootstrap document, start with AGENTS.md.
Project Overview
Session Buddy is a Claude Session Management MCP (Model Context Protocol) server providing comprehensive session management for Claude Code across any project. It operates as a standalone MCP server with isolated environment to avoid dependency conflicts.
Task System
The session-buddy task system is the typed, persistent replacement for the built-in TodoWrite/TaskCreate tool family that Anthropic's upstream API does not advertise for MiniMax-M* models served through https://api.minimax.io/anthropic (server-side tengu_vellum_ash gate; verified 2026-09-29 against the issue trackers linked from the spec). All seven tools live under the mcp__session-buddy__* namespace.
Tools
| Tool | Purpose |
|---|---|
tasks_create(content, tags, owner=None, due=None, priority='normal', effort=None, parent_task_id=None, metadata=None) |
Mint a new task. owner and created_by are server-derived from caller identity (caller-supplied values are silently overwritten). Tags MUST include "task" (Pydantic-validated). Returns a Task whose id matches ^t-[0-9a-f]{32}$. |
tasks_list(status=None, owner=None, tag=None, parent_task_id=None, include_legacy=False, k=20, cursor=None) |
Filter by status/owner/tag with cursor pagination. Server-side: owner is forced to caller_identity regardless of caller input. include_legacy=False by default; legacy tags=["todo"] rows are excluded unless the caller opts in. |
tasks_get(task_id) |
Fetch by id; 404 (not 403) on missing or invisible — no info leak. |
tasks_update(task_id, request: UpdateTaskRequest) |
Mutate mutable fields. Caller-supplied owner / created_by / completed_by are rejected with owner_mutation_forbidden. workflow_id is server-set ONLY by the handoff tool. |
tasks_complete(task_id, result_notes=None) |
Mark as done; owner-only (non-owners get 404). No implicit dispatch — even if result_notes starts with "HANDOFF: ", no workflow is triggered. Use the mahavishnu handoff tool for that. |
tasks_search(query, project=None, min_score=None, k=10) |
Semantic search with quick_search parity (kind=task gate → visibility → min_score). |
tasks_history(task_id, k=50, cursor=None) |
Cursor-paginated change log; returns {items: list[TaskEvent], next_cursor: str | None}. |
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.
- 4d ago Changed · +30 tokens per session 249b27db4c04
- 20d ago Changed · +12 tokens per session cbf1a8ce39f0
- 24d ago Changed · +7 tokens per session cffe427b2d52
- 27d ago Changed · +19 lines · +271 tokens per session a8bb653fd43d
- 1mo ago Changed · -3 tokens per session 3c70167eec25
- 1mo ago Changed 4e6b3ec22169
- 1mo ago Changed · +25 lines · +803 tokens per session 5dff490cb4df
- 1mo ago Changed · -2 tokens per session 9cb54de92004
- 1mo ago Changed · -2 lines · -21 tokens per session 81ac37534e9e
- 2mo ago First seen · 600 lines · 5,400 tokens per session scan A 97f431fe6c81
session-buddy CLAUDE.md is an instructions file published in the GitHub repository lesleslie/session-buddy (4 stars, last pushed 5d ago), licensed BSD-3-Clause. It adds 6,497 tokens to every session, about $0.0260 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.
session-buddy CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| session-buddy CLAUDE.mdlesleslie/session-buddy | Instructions file | 4 | 5d ago | BSD-3-Clause | A | 6,497 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |