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.
git clone --depth 1 https://github.com/JairoTorregrosa/jaiskillsWrote 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.
[](https://agentmods.dev/agents/jairotorregrosa/jaiskills/insistir-researcher)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
- Search
docs/solutions/for past solutions related to your topic (if the directory exists) - Search existing code for patterns, conventions, and prior art (
Glob+Grep) - Read project configuration files (package.json, tsconfig.json, etc.) for version constraints
- 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:
- Identify the specific version in use (from package.json, lock files, or imports)
- Search for deprecation notices, breaking changes, or migration guides
- Flag any APIs or patterns that are deprecated or scheduled for removal
- 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:
- Check official documentation for the specific version in use
- Search for community patterns and recommended approaches
- Look for known issues, gotchas, or performance considerations
- 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)
- ...
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.
- 12d ago First seen · 118 lines · 50 tokens per session scan A 7d116f991799
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.
Other agents, from other repositories
architect
Harness architecture designer that takes project analysis and pattern library input to produce a complete harness specification — agents, skills, hooks, rules, and data flow. Uses opus for deep reasoning about optimal agent team composition.
scout
Fast codebase analyst that explores project structure, tech stack, existing harness components, and development patterns. Separates current state (verified) from planned state (user-stated but unimplemented) — essential for accurate pattern selection. Spawned by create-harness and update-harness skills.
enterprise-orchestrator
Routes any task to the right department and specialist using capability-based routing, risk-classified review, and task-ID-gated work products. Supports Full, Sprint, and Micro pipeline modes with Agent Teams integration.
data-orchestrator
Routes data tasks to data engineers, analysts, QA engineers, or data scientists.
engineering-orchestrator
Routes engineering tasks to backend, frontend, mobile, fullstack, embedded, blockchain, ML engineers, QA, technical writers, support, DevRel, and program management.
finance-orchestrator
Routes finance requests to analysts, accountants, controllers, and corporate development.