What is adversarial-refinement-loop?

An open-ended review process that repeatedly researches, critiques, implements, and verifies changes until the user stops it or useful work is blocked.

Use it when you explicitly want continued refinement across changing review perspectives, with the exact next review lens preserved if the run pauses.

It prevents a single successful build or review pass from being treated as proof that no further problems exist.

adversarial-refinement-loop — Skill for Codex by AkshitIreddy

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 AkshitIreddy/agent-skills --skill adversarial-refinement-loop

Clone the repo

git clone --depth 1 https://github.com/AkshitIreddy/agent-skills

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/akshitireddy/agent-skills/adversarial-refinement-loop/github.svg)](https://agentmods.dev/skills/akshitireddy/agent-skills/adversarial-refinement-loop)

Your own site

<a href="https://agentmods.dev/skills/akshitireddy/agent-skills/adversarial-refinement-loop"><img src="https://agentmods.dev/badge/skills/akshitireddy/agent-skills/adversarial-refinement-loop/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/akshitireddy/agent-skills/adversarial-refinement-loop"><img src="https://agentmods.dev/badge/skills/akshitireddy/agent-skills/adversarial-refinement-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,252 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.

Model	Per session	Once invoked
Fable 5.1	$0.00025	$0.01252
Opus 5.5	$0.00010	$0.00501
Sonnet 5.5	$0.00005	$0.00250
Haiku 4.5	$0.00003	$0.00125

Measured 1mo ago against content hash 54eb65401caf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

adversarial-refinement-loop 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 1mo 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.

skills/adversarial-refinement-loop/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Treat refinement as an open-ended search, not a checklist that converges after one green build. Once invoked, keep starting new passes until the user explicitly pauses or stops, a genuine external blocker prevents useful work, or the host ends the run. A pass with no high-confidence defects is evidence to change the review lens; it is not a completion condition.

An ordinary response boundary, context compaction, temporary tool failure, exhausted lens, or clean result is a checkpoint, not completion. Use a host goal or scheduled continuation only when the user has explicitly requested the corresponding mechanism; ordinary loop execution needs neither. If a hard host stop is unavoidable, label the run incomplete, preserve the exact ledger and next lens, and resume on the next supported continuation. A blocker ends the active run only when no safe, useful pass remains under any lens after reasonable alternatives have been tried.

Away-mode context

Users commonly invoke this loop immediately before going to sleep or becoming busy with something else. Treat their expected silence as permission to keep working within the already authorized scope, not as a request for frequent decisions or a signal to stop. Prefer evidence-backed, reversible assumptions; move to another useful lens when one lane genuinely needs user input. Absence does not expand permission to publish, push, release, contact people, delete data, expose private material, or make other external mutations.

If the user returns and says they are awake, available again, or wants to stop the loop, exit persistent loop mode promptly. Stop scheduling automatic new passes, preserve the current ledger and active findings, and continue any remaining requested work under ordinary collaboration rules unless the user also asks to pause or stop the project itself. Leaving loop mode is not the same as discarding the backlog.

Pass loop

Maintain a lightweight pass ledger containing the lens, evidence, changes, verification, and unresolved hypotheses. For every pass:

Read the full file on GitHub · 109 lines

Files

What ships with it

1 file 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.

agents/openai.yaml 317 B

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.

1mo ago Changed · -1 lines · -18 tokens per session 54eb65401caf
1mo ago First seen · 110 lines · 43 tokens per session scan A 4a8e8868afea

Subscribe to this mod's changes

adversarial-refinement-loop is a skill published in the GitHub repository AkshitIreddy/agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,252 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude Code Code review Research agent-skills ai-agents codex cursor gemini-cli

simplify

This skill should be used when the user asks to "simplify", "clean up the diff", "run simplify", "simplify the changes", "review changed code for cleanup", explicitly invokes "/simplify", or asks to "commit without simplify", "skip simplify for this commit", or "commit this but skip simplify". Reviews changed code…

fcakyon/claude-codex-settings · 97 tokens

chisle-review

Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink. One finding per line, no praise. Use when the user says "chisle review", "review this for bloat", or invokes /chisle-review.