agentmods.dev

insistir

insistir is a skill for Claude Code, Codex from JairoTorregrosa/jaiskills. It costs 34 tokens per session (4,181 once invoked), scanned B, 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 CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Part of the jaiskills plugin — 12 skills, 4 agents, 2 hooks shipped together

not rated 10repo +4 changed 1mo ago B scan 34 tokens original MIT

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 with agentmods
npx agentmods add skills/jairotorregrosa/jaiskills/insistir
View source ↗ JairoTorregrosa/jaiskills
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.

Any agent
npx skills add JairoTorregrosa/jaiskills --skill insistir
Clone the repo
git clone --depth 1 https://github.com/JairoTorregrosa/jaiskills

Made for: Claude Code, Codex.

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

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 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,181 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00034 $0.04181
Opus 5.5 $0.00014 $0.01672
Sonnet 5.5 $0.00007 $0.00836
Haiku 4.5 $0.00003 $0.00418

Measured 1mo ago against content hash 244cde56587c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

insistir scanned grade B with 1 finding 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 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (hooks/reviewer_bash_filter.py, hooks/task_completed.py, 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find ~/.claude/insistir-state/${CLAUDE_SESSION_ID} -maxdepth 1 -name '*.approved' -delete
skills/orchestration/insistir/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

insistir

Task: $ARGUMENTS

You are the tech lead of the pipeline below. Empty task line → get the task in Phase 0.

It pays off for multi-part work that parallelizes across different files. For single-file edits, typos, quick fixes, strictly sequential chains, or tasks that must all edit the same file (parallel workers overwrite each other), tell the user a single session is cheaper and confirm before going on.

Pipeline

LEAD (delegate mode: plans, spawns, routes reports, writes markers; never edits code)
 │
 ├─► worker-t1      worker-t2      worker-t3          implement + commit → done
 │       │              │              │
 ├─► reviewer-t1-r1  reviewer-t2-r1  reviewer-t3-r1   fresh, read-only, never the author
 │       │              │              │               → verdict JSON → done
 ├─► second-opinion judge (cross-provider; skipped on trivial clean approvals)
 │       │
 │   APPROVED ─► T<N>.approved marker ─► TaskUpdate completed (hook-gated)
 │   REVISE   ─► fixer-t<N>-r1 (fresh) ─► reviewer-t<N>-r2 (fresh) ─► judge ─► …
 │              until APPROVED, or max_review_rounds → FAILED (suggest decomposition)
 └─► next wave once dependencies are completed

Invariants

  1. Delegate mode from Phase 2 on. The lead spawns, routes reports, manages tasks and reports to the user. It never reads or edits code, runs builds or tests. Lead Bash is limited to: the mode check, the pre-flight check, the state dir, approval markers, the judge diff, what the second-opinion and file-todos skills run, and insistir.py.
  2. Fresh agent per phase. Every worker, reviewer and fixer is spawned for one job and ends after its report. Nothing is reused or resumed across rounds.
  3. Reviewer is never the author and cannot edit (disallowedTools plus a Bash whitelist hook). Its evidence is the code and the checks it runs, not the worker's report.
  4. Acceptance criteria are the contract. Paste them verbatim into every prompt.
  5. A plan task completes only after an APPROVED outcome, recorded as a marker the TaskCompleted hook checks. Never write a marker to unblock the gate.
  6. Round budget: max_review_rounds (default 2, per-task override). Exhausted = failed.
  7. The judge never blocks the run. Unavailable judge → reviewer verdict stands, recorded.

Read the full file on GitHub · 249 lines

Files

What ships with it

10 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. 1mo ago Changed · -258 lines · -178 tokens per session scan D → B 244cde56587c
  2. 1mo 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 (10 stars, last pushed 4d ago), licensed MIT. It adds 34 tokens to every session and 4,181 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsClaude CodeCode reviewMulti-Agentagentspluginskills
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

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

sip

After you create or change an artifact or skill, taste-test it with our own skills instead of trusting your in-session judgment — recursive self-improvement, made automatic. Use right after writing or editing anything, before calling it done, committing, or handing it off.

LilMGenius/paperthin · 55 tokens

prism

Split one artifact — a claim, plan, or file — across 2 to 5 independent lenses, one per genuinely distinct failure mode (correctness, security, readability, cost, adversarial-user), and return their convergence: where they agree, where they disagree, and the single next question that resolves the disagreement. Use…

LilMGenius/paperthin · 98 tokens

hate

Attack a plan, design, or argument like you want it to fail before you commit real effort — return the single load-bearing objection and the cheapest experiment that would prove it matters, not a checklist. User-invoked on purpose: a hate-it reflex always in the agent's reach would bias it toward demolition. Weighs…

LilMGenius/paperthin · 79 tokens

fabric-spec

Starts a persistent Pi Fabric spec supervisor that audits the main session against a feature design spec and steers only when a requirement lacks verified evidence. Use for strict, unblocked spec compliance while the main agent keeps full freedom to orchestrate.

monotykamary/pi-fabric · 50 tokens