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.
npx skills add majiayu000/vibeguard --skill iterative-retrievalgit clone --depth 1 https://github.com/majiayu000/vibeguardWrote 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.
[](https://agentmods.dev/skills/majiayu000/vibeguard/iterative-retrieval)<a href="https://agentmods.dev/skills/majiayu000/vibeguard/iterative-retrieval"><img src="https://agentmods.dev/badge/skills/majiayu000/vibeguard/iterative-retrieval/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.
<a href="https://agentmods.dev/skills/majiayu000/vibeguard/iterative-retrieval"><img src="https://agentmods.dev/badge/skills/majiayu000/vibeguard/iterative-retrieval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.00884 |
| Opus 5 | $0.00022 | $0.00442 |
| Sonnet 5 | $0.00009 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00088 |
Grade A, and why
iterative-retrieval 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Iterative Retrieval
Overview
In large code bases, one search is often not enough. This skill iterates through a search loop, gradually narrowing the scope and pinpointing the relevant code.
When to Activate
- Research requires multiple searches because the first result set is incomplete or low-confidence.
- A claim depends on current external documentation, issue state, API behavior, or release notes.
- Search results disagree and need a refinement loop before conclusions are trusted.
- A task needs fact/inference separation before implementation or recommendation.
- A first search returns too many partially related results or misses the target surface.
- A codebase question spans file names, symbols, docs, and generated artifacts.
- A user needs evidence-backed repository orientation before implementation.
Red Flags
- The same broad query is repeated without changing terms or scope.
- Low-relevance results are read in depth before high-relevance anchors.
- Search history is lost, so later conclusions cannot be traced back to evidence.
Checklist
- Start with 2-3 concrete keywords from the user request.
- Score search results before expanding into neighboring files.
- Stop after three rounds with an explicit unresolved-questions list.
4 stage cycle
1. DISPATCH (distribution search)
- Extract search keywords from requirements
- Choose a search strategy:
- Glob: Search by filename pattern
- Grep: search by content keywords
- AST: Search by code structure (function name, class name)
- Launch multiple searches in parallel
2. EVALUATE (evaluation result)
Rate each search result (0-1):
| Fraction | Meaning | Action |
|---|---|---|
| 0.8-1.0 | Highly relevant | Reserved, further reading |
| 0.5-0.7 | Partially related | Reserved, extract key information |
| 0.2-0.4 | Low correlation | Record path, not in depth |
| 0.0-0.1 | Not relevant | Discard |
3. REFINE (refined query)
Adjust your search strategy based on the evaluation results:
- Highly relevant results → Expand search in the same directory/same module
- Low relevant results → Change keywords or search strategies
- Discover new clues → Additional searches
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.
- 10d ago First seen · 113 lines · 43 tokens per session scan A 1ab57d288f66
iterative-retrieval is a skill published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 884 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
ring:validating-ux-completeness
Validating that UX specifications are complete before technical design: a read-only checklist over wireframes, states, responsive behavior, accessibility, and component-library alignment, emitting a DESIGN VALIDATED / NEEDS REVISION verdict to design-validation.md. Standalone utility — run after a product-designer…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…
ring:reviewing-docs
Reviewing end-user and product documentation quality across voice/tone, structure, completeness, clarity, and technical accuracy; flags issues with prioritized findings and a pass/needs-revision verdict. Use when reviewing draft docs, running a pre-publication check, auditing existing docs, or enforcing style-guide…