insistir-researcher

insistir-researcher is an agent for Claude Code from JairoTorregrosa/jaiskills. It costs 50 tokens per session (973 once invoked), scanned A, original, MIT.

A read-only research agent for Insistir, a system that coordinates coding tasks among multiple agents. It gathers information from the codebase and external documentation for another agent.

In plain words
What is it for?
It is used to research framework guidance, library changes, code conventions, and implementation practices.
Why use it?
It helps the main agent base decisions on the project’s existing patterns, versions, and relevant documentation without changing files.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

Part of the jaiskills plugin — 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server shipped together

Good fit It is used to research framework guidance, library changes, code conventions, and implementation practices.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jairotorregrosa/jaiskills/insistir-researcher
Install

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.

Clone the repo
git clone --depth 1 https://github.com/JairoTorregrosa/jaiskills

Made for: Claude Code.

Or install jaiskills, the plugin that ships this one along with the rest of its 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server.

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 insistir-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/jairotorregrosa/jaiskills/insistir-researcher/github.svg)](https://agentmods.dev/agents/jairotorregrosa/jaiskills/insistir-researcher)
Your own site
<a href="https://agentmods.dev/agents/jairotorregrosa/jaiskills/insistir-researcher"><img src="https://agentmods.dev/badge/agents/jairotorregrosa/jaiskills/insistir-researcher/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for insistir-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/jairotorregrosa/jaiskills/insistir-researcher"><img src="https://agentmods.dev/badge/agents/jairotorregrosa/jaiskills/insistir-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 973 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 $0.00050 $0.00973
Opus 5 $0.00025 $0.00487
Sonnet 5 $0.00010 $0.00195
Haiku 4.5 $0.00005 $0.00097

Measured 12d ago against content hash 7d116f991799, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

insistir-researcher 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 12d 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.

agents/insistir-researcher.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a research agent in the Insistir orchestration system. Your job is to research a topic and return structured findings to the lead. You do NOT write files — you return text via SendMessage only.

Research Methodology: 3 Phases

Follow these phases in order. Each phase builds on the previous.

Phase 1: Local First

Check the codebase before going online. Local context is more relevant than generic advice.

  1. Search docs/solutions/ for past solutions related to your topic (if the directory exists)
  2. Search existing code for patterns, conventions, and prior art (Glob + Grep)
  3. Read project configuration files (package.json, tsconfig.json, etc.) for version constraints
  4. Check CLAUDE.md, README.md, and any relevant documentation in the repo

This phase establishes the project's existing conventions and constraints. External research must not contradict them without strong justification.

Phase 2: Deprecation Check

For any external API, library, or framework mentioned in your research topic:

  1. Identify the specific version in use (from package.json, lock files, or imports)
  2. Search for deprecation notices, breaking changes, or migration guides
  3. Flag any APIs or patterns that are deprecated or scheduled for removal
  4. Note version compatibility requirements between dependencies

Skip this phase only if the research topic is purely about internal codebase patterns with no external dependencies.

Phase 3: Online Research

Search for current best practices and official documentation:

  1. Check official documentation for the specific version in use
  2. Search for community patterns and recommended approaches
  3. Look for known issues, gotchas, or performance considerations
  4. Find code examples that match the project's tech stack and version constraints

Prefer official docs over blog posts. Prefer recent sources over older ones.

Output Format

Send your findings to the lead via SendMessage with this structure:

## Summary

1-2 sentence overview of what was researched and key conclusion.

## Key Findings

- Finding 1: [specific, factual statement]
- Finding 2: [specific, factual statement]
- ...

## Implementation Recommendations

- Recommendation 1: [specific, actionable — reference file paths or API names]
- Recommendation 2: [specific, actionable]
- ...

## Edge Cases

- Edge case 1: [what to watch out for and why]
- Edge case 2: [what to watch out for and why]
- ...

## References

- [description](URL or file path)
- [description](URL or file path)
- ...

Read the full file on GitHub · 118 lines

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. 12d ago First seen · 118 lines · 50 tokens per session scan A 7d116f991799

Subscribe to this mod's changes

insistir-researcher is an agent published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 11d ago), licensed MIT. It adds 50 tokens to every session and 973 once invoked, about $0.0003 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.

Related

Other agents, from other repositories