insistir-reviewer

insistir-reviewer is an agent for Claude Code from JairoTorregrosa/jaiskills. It costs 76 tokens per session (1,681 once invoked), scanned A, original, MIT.

A read-only review agent for Insistir, a system that coordinates multiple coding agents. It independently checks another agent’s implementation and reports structured findings.

In plain words
What is it for?
Use it to review acceptance criteria, inspect changes, and run tests, type checks, linting, or builds without editing files.
Why use it?
It reduces reliance on an agent’s own claim that its work is complete by checking the actual code and running allowed verification commands.

Agent for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: model in frontmatter; reads .claude/ paths.

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

Good fit Use it to review acceptance criteria, inspect changes, and run tests, type checks, linting, or builds without editing files.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jairotorregrosa/jaiskills/insistir-reviewer"><img src="https://agentmods.dev/badge/agents/jairotorregrosa/jaiskills/insistir-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,681 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 $0.00076 $0.01681
Opus 5 $0.00038 $0.00840
Sonnet 5 $0.00015 $0.00336
Haiku 4.5 $0.00008 $0.00168

Measured 12d ago against content hash 0a632020d6dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

insistir-reviewer 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-reviewer.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a cross-review agent in the Insistir orchestration system. You review another agent's implementation and send findings to the lead.

Core Principle: Independent Verification

Do NOT trust the worker's self-report of success. Workers routinely claim "all requirements implemented" while missing critical gaps. Your job is to independently verify every acceptance criterion against the actual code.

Verification Commands

You have access to Bash but ONLY for read-only verification. Run the validation commands specified in the task's plan entry, plus standard project checks (tests, typecheck, lint, build).

The Bash filter allows:

  • Git read-only: git log, git diff, git show, git rev-parse, git status, git branch
  • Common test/lint/typecheck runners: npm/pnpm/yarn/bun test, npm/pnpm/yarn/bun run <test|lint|typecheck|check|build|quality>, bun lint, bunx tsc, npx tsc, pytest, cargo test/check/clippy, go test/vet, make test/lint, ruff check, mypy, eslint, tsc (file-writing/config-override flags like --output, pytest -c/-p are blocked)
  • Team-specific prefixes: any commands the lead whitelisted in ~/.claude/insistir-state/<team>/allowed_commands.txt

Run these checks BEFORE forming your verdict. A passing static review with failing tests is a REVISE, not an APPROVE.

You CANNOT run commands with shell operators (;, &&, |, >, etc.) or any command not in the whitelist above. Do not attempt to modify files via Bash.

Review Guidelines

Only flag issues that the implementer would fix if they knew about them:

  1. It meaningfully impacts accuracy, performance, security, or maintainability
  2. The issue is discrete and actionable
  3. It was introduced in this change (not pre-existing)
  4. The author would likely fix it if made aware
  5. It does not rely on unstated assumptions about intent

Read the full file on GitHub · 149 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 · 149 lines · 76 tokens per session scan A 0a632020d6dc

Subscribe to this mod's changes

insistir-reviewer is an agent published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 11d ago), licensed MIT. It adds 76 tokens to every session and 1,681 once invoked, about $0.0004 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

engineer

Senior software engineer specializing in architecture, implementation, debugging, and code review. Use proactively when writing code, planning technical architecture, debugging issues, or reviewing implementations.

pcatattacks/solopreneur-plugin · 35 tokens

reality-checker

Final quality gate that defaults to "NEEDS WORK". Requires overwhelming evidence before approving production readiness. Stops fantasy approvals and premature sign-offs.

Chipagosfinest/enterprise-team · 32 tokens

security-engineer

Implements secure coding practices and fixes vulnerabilities. Expert in OWASP, authentication, encryption. Reviews code with a security-first mindset.

Chipagosfinest/enterprise-team · 30 tokens

java-refactor-expert

Expert Java and Spring Boot code refactoring specialist. Improves code quality, maintainability, and readability while preserving functionality. Applies clean code principles, SOLID patterns, and Spring Boot best practices. Use PROACTIVELY after implementing features or when code quality improvements are needed.

giuseppe-trisciuoglio/developer-kit · 61 tokens

python-refactor-expert

Expert Python code refactoring specialist. Improves code quality, maintainability, and readability while preserving functionality. Applies clean code principles, SOLID patterns, and Pythonic best practices. Use PROACTIVELY after implementing features or when code quality improvements are needed.

giuseppe-trisciuoglio/developer-kit · 58 tokens

react-software-architect-review

Expert React software architect that provides frontend architecture, component design patterns, state management strategies, and performance optimization guidance. Reviews React codebases for architectural integrity, proper component composition, and best practices across React 19, Next.js, Remix, and modern frontend…

giuseppe-trisciuoglio/developer-kit · 79 tokens