insistir

insistir is a skill for Claude Code from JairoTorregrosa/jaiskills. It costs 212 tokens per session (6,308 once invoked), scanned D, original, MIT.

A multi-agent review workflow in which fresh agents independently check, revise, and judge each other's work.

In plain words
What is it for?
Use it for complex coding tasks that need implementation, adversarial review, revision rounds, and a final cross-provider verdict.
Why use it?
Repeated independent review can expose mistakes or missed requirements before the result is accepted.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

Good fit Use it for complex coding tasks that need implementation, adversarial review, revision rounds, and a final cross-provider verdict.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add JairoTorregrosa/jaiskills
Claude Code
/plugin install 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

README.md
[![agentmods](https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/insistir/github.svg)](https://agentmods.dev/skills/jairotorregrosa/jaiskills/insistir)
Your own site
<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/insistir"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/insistir/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/insistir"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/insistir.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,308 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00212 $0.06308
Opus 5 $0.00106 $0.03154
Sonnet 5 $0.00042 $0.01262
Haiku 4.5 $0.00021 $0.00631

Measured 12d ago against content hash e649b6d07315, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade D, and why

insistir scanned grade D with 2 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/insistir.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

Workers can edit files and run any commands. Reviewers **cannot edit** (`disallowedTools: Edit, Write`) but can run whitelisted read-only verification commands (tests, typecheck, lint) via a `PreToolUse` Bash filter hook

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Wait another 10 seconds. If still no response, proceed with force cleanup — remove team/task directories file-by-file (avoid `rm -rf` on home paths as security hooks may block it):
skills/orchestration/insistir/SKILL.md · 507 lines

How it starts

The opening of the file, as written. The whole thing — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Insistir: Agents Checking Agents

Multi-agent orchestration where every agent's work is reviewed by a different agent in an iterative adversarial loop — the reviewer either APPROVES or sends back for REVISION, with fresh context each round.

Uses Claude Code Agent Teams — each teammate is a full independent Claude Code session with its own context window, communicating via messages and a shared task list.

Adversarial Cooperation Model

Based on dialectical autocoding research: a structured coach/player feedback loop where the reviewer (coach) independently validates against requirements, catching the implementer's (player's) blind spots and false confidence. Key principles:

  1. Fresh context each round — each reviewer spawn starts clean, avoiding context pollution
  2. Requirements contract — acceptance criteria are the single source of truth, not the worker's self-assessment
  3. Iterative convergence — multiple review rounds systematically close the delta between implementation and requirements
  4. Turn limits as complexity signal — if max rounds exhaust without approval, the task is likely too complex and should be decomposed
  5. Cross-provider judgment — a different model family (Codex/GPT-5) issues the final verdict, eliminating self-preference bias

Custom Agents (bundled in this plugin)

Agent Role Tools Model
jaiskills:insistir-worker Implement task or apply review fixes, commit, report to lead, shut down Read, Edit, Write, Bash, Glob, Grep, WebFetch, WebSearch, SendMessage, TaskGet (disallowed: TaskUpdate, TaskCreate, TaskList) opus
jaiskills:insistir-reviewer Cross-review with APPROVE/REVISE verdict, run verification commands Read, Glob, Grep, Bash (whitelisted), SendMessage, TaskGet opus
jaiskills:insistir-learnings-researcher Search docs/solutions/ for relevant past solutions (read-only) Read, Glob, Grep, SendMessage opus
jaiskills:insistir-researcher Research best practices and framework docs (read-only + web) Read, Glob, Grep, WebFetch, WebSearch, SendMessage opus

Read the full file on GitHub · 507 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 507 lines · 212 tokens per session scan D e649b6d07315

Subscribe to this mod's changes

insistir is a skill published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 11d ago), licensed MIT. It adds 212 tokens to every session and 6,308 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it D with 2 findings (unrestricted tool access, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

review

Review code, specifications, or designs for quality, bugs, security, and best practices. Use when the user wants feedback on recent work, a pull request, or any artifact.

pcatattacks/solopreneur-plugin · 38 tokens

sonarqube-mcp

Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…

giuseppe-trisciuoglio/developer-kit · 127 tokens

nestjs-code-review

Provides comprehensive code review capability for NestJS applications, analyzing controllers, services, modules, guards, interceptors, pipes, dependency injection, and database integration patterns. Use when reviewing NestJS code changes, before merging pull requests, after implementing new features, or for…

giuseppe-trisciuoglio/developer-kit · 82 tokens

nextjs-code-review

Provides comprehensive code review capability for Next.js applications, validates Server Components, Client Components, Server Actions, caching strategies, metadata, API routes, middleware, and performance patterns. Use when reviewing Next.js App Router code changes, before merging pull requests, after implementing…

giuseppe-trisciuoglio/developer-kit · 86 tokens

react-code-review

Provides comprehensive code review capability for React applications, validates component architecture, hooks usage, React 19 patterns, state management, performance optimization, accessibility compliance, and TypeScript integration. Use when reviewing React code changes, before merging pull requests, after…

giuseppe-trisciuoglio/developer-kit · 81 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens