iterative-retrieval SKILL.md skillA

iterative-retrieval from jnpiyush/agentx is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jnpiyush/agentx/iterative-retrieval@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jnpiyush/agentx
Path
.github/skills/ai-systems/iterative-retrieval/SKILL.md
Versions recorded
5
Latest version
v1.0.0, committed Sep 25, 2026
First version recorded
May 18, 2026
Size
6,921 bytes
Repository stars
19
License
Apache-2.0

Progressive context refinement for subagents and tool-using LLMs. Use when a parent agent must delegate research, code reading, or document Q&A to a subagent with a tight context budget. Replaces one-shot context dumps with a query -> retrieve -> filter -> requery loop that returns only the evidence the parent needs.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Iterative Retrieval for Subagents

> **Purpose**: Keep subagent context budgets small while still answering the parent agent's real question.
> **Scope**: Subagent delegation, RAG-style scoped reads, multi-pass code search, evidence extraction.

---

## When to Use This Skill

- Parent agent needs a subagent to read large files, long docs, or many search hits and return a short answer.
- The naive approach ("here is the whole repo, summarize") will blow the subagent context.
- The question is open enough that one search query will miss relevant evidence.
- Answer must cite specific files, lines, or sections, not just produce a paraphrase.

## When NOT to Use

- Single-file edits where you can read the file directly.
- Questions answerable from titles or filenames alone.
- Tasks where the parent agent already has the relevant content in context.

## The Anti-Pattern (One-Shot Context Dump)

```
Parent: "Read these 40 files and tell me where auth is handled."
  -> subagent loads 40 files
  -> hits context limit at file 17
  -> hallucinates the rest, or returns truncated nonsense
```

This fails because:
- Subagent burns budget on irrelevant files before reaching the answer.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jnpiyush/agentx/iterative-retrieval@sha256:689e72f247024fba

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_jxsdl2hvbqggpfnd.svg)](https://markdownregistry.com/a/art_jxsdl2hvbqggpfnd)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 5 versions of this file, between May 18, 2026 and Sep 25, 2026, about one every 33 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-09-25 244da72 6,921 BA view · diff
v1.0.02026-09-15 f17c505 6,919 BA view · diff
v1.0.02026-05-31 7518f76 6,915 BA view · diff
v1.0.02026-05-30 55f7137 6,846 BA view · diff
v1.0.02026-05-18 6c28d61 6,836 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6921 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jnpiyush/agentx · 19 stars · license Apache-2.0 · pushed 2026-11-04 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_jxsdl2hvbqggpfnd
GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/iterative-retrieval
GET https://markdownregistry.com/api/v1/blob/689e72f247024fba6aaa9202025897d2a1cc4e2bade772d4ddd56a6c1d746477

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jnpiyush/agentx

000-frontier-core Cursor rule
jnpiyush/agentx · .cursor/rules/000-frontier-core.mdc · Frontier canonical contracts and workspace context for Cursor.
git:20261012.38fb931 · audit A · 19 stars
ai Cursor rule
jnpiyush/agentx · .cursor/rules/ai.mdc · AI / agent / LLM workflow standards (Frontier)
git:20261010.87e53aa · audit A · 19 stars
csharp Cursor rule
jnpiyush/agentx · .cursor/rules/csharp.mdc · C# / .NET coding standards (Frontier)
git:20261010.87e53aa · audit A · 19 stars
python Cursor rule
jnpiyush/agentx · .cursor/rules/python.mdc · Python coding standards (Frontier)
git:20261010.87e53aa · audit A · 19 stars
react Cursor rule
jnpiyush/agentx · .cursor/rules/react.mdc · React / TSX frontend standards (Frontier)
git:20261010.87e53aa · audit A · 19 stars
typescript Cursor rule
jnpiyush/agentx · .cursor/rules/typescript.mdc · TypeScript / Node backend standards (Frontier)
git:20261010.87e53aa · audit A · 19 stars
agent-memory-systems SKILL.md skill
jnpiyush/agentx · .github/skills/ai-systems/agent-memory-systems/SKILL.md · Design agent memory beyond a single context window: short-term (working / scratchpad), long-term (episodic, semantic…
v1.0.0 · audit A · 19 stars
agent-observability SKILL.md skill
jnpiyush/agentx · .github/skills/ai-systems/agent-observability/SKILL.md · Instrument LLM agents with tracing, metrics, and evaluation telemetry. Use when adding OpenTelemetry GenAI semantic…
v1.0.0 · audit A · 19 stars
ai-agent-development SKILL.md skill
jnpiyush/agentx · .github/skills/ai-systems/ai-agent-development/SKILL.md · Build production-ready AI agents with Microsoft Foundry and Agent Framework. Use when creating AI agents, selecting LLM…
git:20261010.87e53aa · audit A · 19 stars
ai-evaluation SKILL.md skill
jnpiyush/agentx · .github/skills/ai-systems/ai-evaluation/SKILL.md · Use when evaluating AI quality, safety, completeness and cost with held-out tasks, executable graders, calibrated…
v1.1.0 · audit A · 19 stars
ai-safety-and-red-teaming SKILL.md skill
jnpiyush/agentx · .github/skills/ai-systems/ai-safety-and-red-teaming/SKILL.md · Defend LLM systems against prompt injection, jailbreaks, data exfiltration, and unsafe output. Covers input/output…
v1.0.0 · audit B · 19 stars
anthropic-claude SKILL.md skill
jnpiyush/agentx · .github/skills/ai-systems/anthropic-claude/SKILL.md · Implement production applications with Anthropic Claude models -- Messages API, tool use, prompt caching, adaptive…
v1.0.0 · audit A · 19 stars

Every file in jnpiyush/agentx

Other files named iterative-retrieval

iterative-retrieval SKILL.md skill
bradygaster/squad · .github/skills/iterative-retrieval/SKILL.md · Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to…
git:20260913.8b79211 · audit A · 3,337 stars
iterative-retrieval SKILL.md skill
bradygaster/squad · packages/squad-cli/templates/skills/iterative-retrieval/SKILL.md · Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to…
git:20260328.87e9381 · audit A · 3,337 stars
iterative-retrieval SKILL.md skill
bradygaster/squad · packages/squad-sdk/templates/skills/iterative-retrieval/SKILL.md · Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to…
git:20260328.87e9381 · audit A · 3,337 stars
iterative-retrieval SKILL.md skill
bradygaster/squad · .squad-templates/skills/iterative-retrieval/SKILL.md · Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to…
git:20260910.9cf5842 · audit A · 3,337 stars
iterative-retrieval SKILL.md skill
hashgraph-online/awesome-codex-plugins · plugins/Colin4k1024/tsp/skills/iterative-retrieval/SKILL.md · Pattern for progressively refining context retrieval to solve the subagent context problem
git:20260512.6523792 · audit A · 1,537 stars
iterative-retrieval SKILL.md skill
microsoft/waza · .github/skills/iterative-retrieval/SKILL.md · Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to…
git:20261016.42d1b9f · audit A · 1,500 stars
iterative-retrieval SKILL.md skill
aaaaqwq/agi-super-team · plugins/agi-super-team-codex/skills/iterative-retrieval/SKILL.md · Progressively refine codebase and evidence retrieval for agents using dispatch, evaluation, query refinement, and…
git:20260721.4bfa205 · audit A · 115 stars
iterative-retrieval SKILL.md skill
frankxai/agentic-creator-os · .claude/skills/iterative-retrieval/SKILL.md · Pattern for progressively refining context retrieval to solve the subagent context problem
git:20260328.03dc5c1 · audit A · 12 stars

Browse by kind, by grade A, or by owner.