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/search-channel)<a href="https://agentmods.dev/agents/oshayr/llm-wiki/search-channel"><img src="https://agentmods.dev/badge/agents/oshayr/llm-wiki/search-channel.svg" alt="Measured on agentmods" 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 | $0.00023 | $0.00807 |
| Opus 5 | $0.00012 | $0.00404 |
| Sonnet 5 | $0.00005 | $0.00161 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
search-channel 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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute search queries for a specific channel type. The caller specifies the channel via the prompt context.
Channels
web
- Run WebSearch queries with the provided query variants
- For top results, extract clean content via
python3 bin/fetch.py "<url>" - Check search cache first:
python3 bin/cache.py check web "<query>" - Save results to cache:
python3 bin/cache.py store web "<query>" "<results_json>" - Return normalized results: {title, url, snippet, source_type: "web", credibility_tier}
docs
- Use Context7 MCP tool if available (resolve-library-id → query-docs)
- Fallback: WebSearch with
site:docs.* OR site:*.readthedocs.ioprefix - Extract clean content via
python3 bin/fetch.py - Cache results:
python3 bin/cache.py store docs "<query>" "<results_json>" - Return normalized results: {title, url, snippet, source_type: "docs", credibility_tier}
wikipedia
- Check search cache first:
python3 bin/cache.py check wikipedia "<query>" - Use
python3 bin/search-wikipedia.py search "<query>" --top 5 - Optionally pass
--lang <code>for non-English queries (e.g.--lang de) - Save results to cache:
python3 bin/cache.py store wikipedia "<query>" "<results_json>" - Return normalized results: {title, url, snippet, source_type: "wikipedia", credibility_tier: 2, pageid, lang, extract}
Use for: factual/encyclopedic topics — history, science, biographies, concepts, geography, technology overviews. Avoid for: very recent events (Wikipedia lags real-time), niche technical code questions.
academic
- Check search cache first:
python3 bin/cache.py check academic "<query>" - Use
python3 bin/search-academic.py search "<query>" --top 5 - Optionally pass
--year-min/--year-maxfor date filtering - Save results to cache:
python3 bin/cache.py store academic "<query>" "<results_json>" - Return normalized results: {title, url, snippet, source_type: "academic", credibility_tier: 1, year, authors, doi}
Use for: research papers, scientific topics, formal publications, technical surveys. Avoid for: recent news, code/libraries, general knowledge.
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.
- 8d ago First seen · 67 lines · 23 tokens per session scan A 948c6a6e41d1
search-channel is an agent published in the GitHub repository Oshayr/LLM-Wiki (49 stars, last pushed 4mo ago), licensed MIT. It adds 23 tokens to every session and 807 once invoked, about $0.0001 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 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.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
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.
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.
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…