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.
npx agentmods add instructions/lesleslie/session-buddy/agents-mdgit clone --depth 1 https://github.com/lesleslie/session-buddyWhat 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 | $0.00658 | $0.00658 |
| Opus 5 | $0.00329 | $0.00329 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade B, and why
session-buddy AGENTS.md scanned grade B with 1 finding 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 2d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- Store MCP client configs as `example.mcp.json` derivatives and keep secrets out of version control. How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
session_buddy/hosts the runtime server (server.py), CLI entrypoint (cli.py), and integration adapters such ascrackerjack_integration.py.- Feature logic belongs in
session_buddy/core/,session_buddy/tools/, andsession_buddy/utils/; keep new modules narrow, protocol-driven, and well-typed. - Tests reside in
tests/with fixtures undertests/fixtures/and strategy notes intests/README.md; mirror package paths when adding cases. - Documentation lives in
docs/; generated assets (dist/,htmlcov/, coverage outputs) should remain untouched.
Build, Test, and Development Commands
uv sync --group devinstalls reproducible runtime and development dependencies.uv run session-buddy startboots the MCP server locally;uv run session-buddy statusconfirms port 8678.uv run pre-commit run --all-filesexecutes Ruff, Pyright, Bandit, Complexipy, and related quality gates while applying safe fixes.- Use Crackerjack as the canonical repo-wide quality and CI/CD gate when validating larger changes or matching CI locally.
uv run pytest --cov=session_buddy --cov-report=term-missingruns the suite with coverage; append--maxfail=1during rapid iteration.
Coding Style & Naming Conventions
- Target Python 3.13 with explicit type hints; import typing as
import typing as tand reference annotations viat.prefixes. - Prefer
pathlib.Path, f-strings, dataclasses, and protocol interfaces; avoid docstrings unless an API contract demands them. - Keep functions short (cognitive complexity ≤13), adopt descriptive snake_case, and consolidate shared helpers within
utils/.
Testing Guidelines
- Pair every module with pytest cases that mirror its path (e.g.,
session_buddy/foo.py→tests/unit/test_foo.py). - Reuse the async fixtures provided; mark temporary failures with
@pytest.mark.xfailand link the tracking issue. - Maintain the march toward 85% coverage; regenerate HTML via
uv run pytest --cov ... --cov-report=htmland reviewhtmlcov/index.htmlbefore submitting.
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.
- 2d ago First seen · 41 lines · 658 tokens per session scan B f7618eb9fdcf
session-buddy AGENTS.md is an instructions file published in the GitHub repository lesleslie/session-buddy (2 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 658 tokens to every session, about $0.0033 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.