pmcp: Agent for OpenCode

.opencode/agent/research-spark.md

research-spark is an agent for OpenCode from Consiliency/pmcp. It costs 17 tokens per session (143 once invoked), scanned A, original, MIT.

A research agent for quickly finding facts in documentation, schemas, APIs, tool descriptions, and codebases.

In plain words
What is it for?
Use it for bounded searches, quick codebase reconnaissance, documentation lookup, and concise findings with suggested next steps.
Why use it?
It provides a focused way to gather relevant information while recording file paths or commands, uncertainties, confidence, and conflicts between documentation and observed behavior.

Agent for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: model in frontmatter; mentions subagents; mentions Codex.

This is Consiliency/pmcp's own configuration. It tells OpenCode how to work on pmcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pmcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Consiliency/pmcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Consiliency/pmcp/main/.opencode/agent/research-spark.md
Clone the repo
git clone --depth 1 https://github.com/Consiliency/pmcp

Made for: OpenCode.

Wrote 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.

agentmods badge for research-spark

README.md
[![agentmods](https://agentmods.dev/badge/agents/consiliency/pmcp/research-spark.svg)](https://agentmods.dev/agents/consiliency/pmcp/research-spark)
Your own site
<a href="https://agentmods.dev/agents/consiliency/pmcp/research-spark"><img src="https://agentmods.dev/badge/agents/consiliency/pmcp/research-spark.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 143 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.00143
Opus 5 $0.00009 $0.00072
Sonnet 5 $0.00003 $0.00029
Haiku 4.5 $0.00002 $0.00014

Measured yesterday against content hash ab05b93bb70c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

research-spark 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.

.opencode/agent/research-spark.md · 20 lines

What it actually says

You are a speed-focused research subagent.

Mission

  • Rapidly gather high-signal facts from code, docs, and tool schemas.
  • Return concise findings with citations to file paths or commands.

Approach

  • Prefer focused searches and bounded file reads.
  • Use Context7 and PMCP tools when framework docs are needed.
  • Surface assumptions and confidence level.
  • Flag conflicts between docs and observed behavior.

Deliverable

  • 5-12 bullets covering facts, uncertainties, and recommended next action.
Changes

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.

  1. yesterday First seen · 20 lines · 17 tokens per session scan A ab05b93bb70c

Subscribe to this mod's changes

research-spark is an agent published in the GitHub repository Consiliency/pmcp (20 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 143 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 2026-09-06.

Related

Other agents, from other repositories