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/dev-russo/session-handoff-mcp/agents-mdgit clone --depth 1 https://github.com/Dev-Russo/session-handoff-mcpWhat 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 | $0.00614 | $0.00614 |
| Opus 5 | $0.00307 | $0.00307 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
session-handoff-mcp AGENTS.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 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.
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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
The project is a Node.js 24+ TypeScript MCP server. Production code lives in src/, organized by responsibility: mcp/ exposes tools, services/ coordinates use cases, checkpoint/ owns schemas and Markdown rendering, project/ resolves project identity, and storage/, security/, config/, and git/ provide infrastructure. Tests live in tests/ and generally mirror a subsystem, for example tests/checkpoint-service.test.ts. Normative behavior belongs in docs/SDD.md; architectural rationale belongs in docs/decisoes-v1.md. Generated output (dist/, coverage/, package archives) must not be committed.
Build, Test, and Development Commands
pnpm install --frozen-lockfile: install exactly the locked dependencies.pnpm dev init --help: run the TypeScript CLI directly during development.pnpm build: compilesrc/intodist/.pnpm test: build and run the Vitest suite once.pnpm test:coverage: run tests with the enforced V8 coverage thresholds.pnpm check: run typecheck, ESLint, Prettier verification, build, and tests.npm pack --dry-run: verify the public npm package contents.
Run pnpm check before submitting changes.
Coding Style & Naming Conventions
Use strict TypeScript and ES modules. Prettier controls formatting; do not hand-align code. ESLint enforces typed rules and type-only imports. Use two-space indentation, camelCase for values/functions, PascalCase for types/classes, and kebab-case filenames such as checkpoint-store.ts. Keep MCP adapters thin and place business behavior in services. Represent recoverable failures with SessionHandoffError and stable uppercase codes.
Testing Guidelines
Vitest files use the *.test.ts suffix. Add unit tests for validation and edge cases, plus integration coverage for MCP or filesystem behavior. Use temporary directories and fictitious project data; never include real client paths or secrets. Coverage must remain at least 80% statements, 70% branches, 85% functions, and 80% lines.
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 · 34 lines · 614 tokens per session scan A ae1f509748a8
session-handoff-mcp AGENTS.md is an instructions file published in the GitHub repository Dev-Russo/session-handoff-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 614 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
codex-pets AGENTS.md
Instructions for astandrik/codex-pets, covering agents.md, commands (verified), workflow, file map and golden samples (follow these patterns).
trusty-squire CLAUDE.md
Instructions for Trusty-Squire/trusty-squire, covering claude.md, project overview, objective function (what this project optimizes for), current state and production, deployed, verified end-to-end.
hoi4-agent-tools AGENTS.md
Instructions for klimPaskov/hoi4-agent-tools, covering project instructions, engineering boundaries, code and tests and documentation and releases.
idesense CLAUDE.md
Instructions for vcth4nh/idesense, covering idesense, agent rules and where things live.
anydocs AGENTS.md
AGENTS.md instructions for kiyeonjeon21/anydocs, covering anydocs, a mounted server the agent never calls is worth nothing, the one number that matters, failure must be loud and and a dead end is the loudest failure of all.
mcp-light-memory AGENTS.md
AGENTS.md instructions for PeterPirog/mcp-light-memory, covering agent operating contract and persistent agent memory: mcp light memory (internalrag).