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 agents/reasonkit/reasonkit-core/handoff_protocolgit clone --depth 1 https://github.com/reasonkit/reasonkit-coreWhat 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 | $0.00000 | $0.00431 |
| Opus 5 | $0.00000 | $0.00216 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
HANDOFF_PROTOCOL 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- HANDOFF_PROTOCOL — 100% identical, 0 lines differ
What it actually says
AGENT HANDOFF PROTOCOL
PURPOSE
To ensure seamless context transfer between specialized agents in the ReasonKit Swarm.
THE HANDOFF TRIGGER
When an agent reaches the boundary of its domain, it MUST initiate a handoff.
Trigger Examples
- Architect -> Rust Engineer: "Architecture defined. Proceed to implementation."
- Rust Engineer -> QA Engineer: "Implementation complete. Verify quality gates."
- Researcher -> Architect: "Research complete. Synthesize into roadmap."
- Any -> Task Master: "Work identified. Create tracking tasks."
HANDOFF FORMAT
When handing off, the active agent must provide a Context Block:
**HANDOFF TO:** [Target Agent Name]
**CONTEXT:** [1-sentence summary of current state]
**ARTIFACTS:**
- [File Path 1] (Created/Modified)
- [File Path 2] (Reference)
**NEXT ACTION:** [Specific instruction for the next agent]
AGENT CAPABILITIES MATRIX
| From Agent | To Agent | Typical Trigger |
|---|---|---|
| Architect | Rust Engineer | Implementation of core logic |
| Architect | Python Specialist | Implementation of glue/scripts |
| Rust Engineer | QA Engineer | Pre-merge verification |
| Python Specialist | QA Engineer | Testing scripts/bindings |
| QA Engineer | DevOps SRE | Release/Deployment |
| DevOps SRE | Security Guardian | Infrastructure Audit |
| Researcher | Architect | Strategic planning |
INSTRUCTIONS FOR HUMANS
If you see a HANDOFF TO message:
- Copy the Context Block.
- Paste it into the chat.
- Activate the requested agent (via
LOADER.mdor manual context switch).
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.
- yesterday First seen · 51 lines · 0 tokens per session scan A 757407cf08cc
HANDOFF_PROTOCOL is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 431 tokens. 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 agents, from other repositories
supply-chain-analyst
Software supply-chain security expert. Deep on Socket.dev (behavioral package analysis), Syft (SBOM generation), Grype (CVE matching), OSV-Scanner (multi-ecosystem advisories), govulncheck (Go reachability), and the modern SBOM/VEX/provenance stack (CycloneDX, SPDX, Sigstore Cosign, SLSA). Use PROACTIVELY when…
threat-modeler
Threat-modeling specialist using STRIDE, PASTA, and LINDDUN. Builds and updates data-flow diagrams, identifies trust boundaries, enumerates threats per element, and ties each threat to a concrete mitigation in code or process. Use PROACTIVELY when designing a new feature, evolving an existing system, authoring or…
database-reviewer
Review schema changes and migrations with team patterns.
index
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
claude
This project has slash commands available in Claude Code.
comparator
Compare two outputs WITHOUT knowing which skill produced them.