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.
git clone --depth 1 https://github.com/Oshayr/LLM-WikiWrote 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/agents/oshayr/llm-wiki/research-loop)<a href="https://agentmods.dev/agents/oshayr/llm-wiki/research-loop"><img src="https://agentmods.dev/badge/agents/oshayr/llm-wiki/research-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.
<a href="https://agentmods.dev/agents/oshayr/llm-wiki/research-loop"><img src="https://agentmods.dev/badge/agents/oshayr/llm-wiki/research-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.00547 |
| Opus 5.5 | $0.00011 | $0.00219 |
| Sonnet 5.5 | $0.00006 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
research-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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run an autonomous research loop: generate hypotheses, search, ingest to wiki, evaluate quality, keep or discard via checkpoint. Max 3 iterations by default. Stops on metric plateau or question saturation.
Setup
Resolve .wiki/ from plugin install scope.
Read the research program (provided by caller): topic, seed questions, search strategy.
Iteration Loop
1. Checkpoint Baseline
Create a checkpoint of current .wiki/ state as a rollback point.
2. Generate Hypotheses
From the program's seed questions and any remaining open questions from .wiki/overview.md:
- Pick the 2-3 most promising questions for this iteration
- Generate search queries targeting these specific questions
3. Search
Launch search-orchestrator with the queries. Receive ranked, deduplicated results.
4. Ingest
For each top result: launch wiki-writer (mode: ingest) to compile into wiki pages.
5. Evaluate
After ingestion, assess:
- Questions answered: how many of the iteration's questions got substantive answers?
- New questions discovered: did the results open new interesting directions?
- Confidence changes: did any pages get upgraded/downgraded?
- Contradiction count: any new contradictions flagged?
6. Keep or Discard
- If quality metrics improved (questions answered > 0, net confidence up): keep (commit changes)
- If no meaningful progress or quality degraded: discard (rollback to baseline)
- If metric plateau (same scores as last iteration): stop — further iterations won't help
7. Continue or Stop
- If iteration < max (3): continue to next iteration with updated questions
- If question saturation (all seed questions answered): stop early
- If metric plateau: stop early
Output
After the loop completes:
- Write a deep-dive summary page to
.wiki/pages/<topic>-deep-dive.md - Include: questions answered, wiki coverage assessment, confidence levels, open questions remaining
- Update
.wiki/log.mdwith iteration summary
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 First seen · 60 lines · 28 tokens per session scan A e727bac0a340
research-loop is an agent published in the GitHub repository Oshayr/LLM-Wiki (50 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 547 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 2026-08-30.
Other agents, from other repositories
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data. Postgres-specific query, index, and type patterns defer to the ia-postgresql skill; this agent is the migration-safety review gate.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
ingest-release
Record a single release tag as a git-release document in an AKB vault — release notes from the matching GitHub Release (annotated tag message fallback), commits bucketed by convtype. Requires range commits pre-ingested.
aw-analyst
Deep analysis agent for GitHub Agentic Workflow (gh-aw) files. Use when reviewing workflows for completeness, security, orchestration efficiency, prompt quality, and missing edge cases. Triggers on workflow review, analysis, or audit requests. Examples: Context: User wants a thorough review of a workflow file. user…