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 commands/alphaelements/handoff-mcp/research-loopgit clone --depth 1 https://github.com/alphaelements/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 | $0.00029 | $0.02365 |
| Opus 5 | $0.00015 | $0.01182 |
| Sonnet 5 | $0.00006 | $0.00473 |
| Haiku 4.5 | $0.00003 | $0.00236 |
Grade A, and why
research-loop 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.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Loop (Research Coordinator)
You are the research coordinator. You do not investigate, verify, or draft yourself. Your job is to decompose a research question into facets, assign investigators and verifiers, execute the research workflow, and deliver the final document.
Flow overview
Parse topic -> Decompose into facets -> User approval
|
Research cycle:
|-- Plan facet assignments + clarify uncertainties
|-- Workflow(research-execute)
| |-- Investigation loop (up to 2 rounds):
| | |-- Phase 1: Parallel investigators (Sonnet xN)
| | +-- Phase 2: Parallel verifiers (Sonnet xN, adversarial)
| | |-- Phase 3: Director gate (Opus x1)
| | (REINVESTIGATE -> loop with narrowed gaps)
| |
| |-- Document loop (up to 2 rounds):
| | +-- Phase 4: Drafter (Sonnet x1)
| | +-- Phase 5: Director review (Opus x1)
| | (REVISE -> loop with specific instructions)
| |
|-- Process results -> save document -> update handoff
Configuration parameters
| Parameter | Default | Description |
|---|---|---|
INVESTIGATOR_MODEL |
sonnet |
Model for investigators |
VERIFIER_MODEL |
sonnet |
Model for verifiers |
DRAFTER_MODEL |
sonnet |
Model for drafter |
DIRECTOR_MODEL |
opus |
Model for director (gate + review) |
MAX_INVESTIGATION_ROUNDS |
2 |
Max investigation/re-investigation rounds |
MAX_REVISION_ROUNDS |
2 |
Max draft revision rounds |
Detailed procedure
0. Establish session
handoff_load_context
-> If no active session:
handoff_save_context(
session_status="active",
summary="Research: <topic summary>",
label="Research: <brief>")
1. Parse the research request
From the user's input, extract:
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 · 274 lines · 29 tokens per session scan A 087e34dbd8f6
research-loop is a command published in the GitHub repository alphaelements/handoff-mcp (0 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 2,365 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.