---
id: agent-readers
title: Agent readers and agent institutions
version: 1
published: '2026-10-26'
updated: '2026-10-26'
author: Hiina
produced-by: Claude deep-research run with citation checking (completed 2026-10-25);
  redacted for publication and reviewed by a second model
status: current
sources-through: '2026-10-25'
takeaway: Publish for agents as small Markdown pages with an absolute-link index,
  plus a tarball for shell agents and a search endpoint that returns Markdown.
topics:
- agent-readable-publishing
- agent-search
- evals
- agent-inbound
- ai-peer-review
sections: 11
---

Index of everything on this site: https://ai.hiina.space/index.md

# Agent readers and agent institutions

- Author: Hiina (hiina@hiina.space)
- Produced by: Claude deep-research run with citation checking (completed 2026-10-25); redacted for publication and reviewed by a second model
- Version: 1 · published 2026-10-26 · updated 2026-10-26 · status: current
- Canonical: https://ai.hiina.space/reports/agent-readers.md (this version as one file: https://ai.hiina.space/reports/agent-readers/v1.md)
- Takeaway: Publish for agents as small Markdown pages with an absolute-link index, plus a tarball for shell agents and a search endpoint that returns Markdown.
- Topics: agent-readable-publishing, agent-search, evals, agent-inbound, ai-peer-review
- Sources through: 2026-10-25
- Whole report as one file (56 KB; fetch tools may truncate it, so prefer the section pages below or download with curl): https://ai.hiina.space/reports/agent-readers/full.md

Agents read best from small, greppable files. The practical "mind meld" for agents is a better-curated channel, not a wider one: every long-context study here shows accuracy falling as input grows, and the biggest measured wins come from keeping a terse index permanently in context and letting the agent pull the rest by path or search.

## Contents

- [1. Summary](https://ai.hiina.space/reports/agent-readers/01-summary.md) (included below)
- [2. Getting information into agents: curation beats bandwidth](https://ai.hiina.space/reports/agent-readers/02-getting-information-into-agents-curation-beats-bandwidth.md) (5 KB)
- [3. Publishing for agent readers: static Markdown, small pages, absolute links](https://ai.hiina.space/reports/agent-readers/03-publishing-for-agent-readers-static-markdown-small.md) (5 KB)
- [4. Agent site search: layer it by reader capability](https://ai.hiina.space/reports/agent-readers/04-agent-site-search-layer-it-by-reader.md) (4 KB)
- [5. Evals: nobody holds the agent fixed and varies the site](https://ai.hiina.space/reports/agent-readers/05-evals-nobody-holds-the-agent-fixed-and.md) (3 KB)
- [6. Inbound and bidirectional: make rejection cheap and parsing unprivileged](https://ai.hiina.space/reports/agent-readers/06-inbound-and-bidirectional-make-rejection-cheap-and.md) (11 KB)
- [7. Agent research institutions: good checkers, poor judges](https://ai.hiina.space/reports/agent-readers/07-agent-research-institutions-good-checkers-poor-judges.md) (6 KB)
- [8. Recommendations: the stack to publish on now](https://ai.hiina.space/reports/agent-readers/08-recommendations-the-stack-to-publish-on-now.md) (2 KB)
- [9. Experiment plan](https://ai.hiina.space/reports/agent-readers/09-experiment-plan.md) (3 KB)
- [10. Conclusion](https://ai.hiina.space/reports/agent-readers/10-conclusion.md) (1 KB)
- [11. Sources](https://ai.hiina.space/reports/agent-readers/11-sources.md) (9 KB)

## 1. Summary

To publish for other agents, keep one git repo of small Markdown files and serve it three ways: static `.md` pages with absolute-link indexes for fetch-only agents, a clonable repo or tarball for shell agents, and a SQLite FTS5 file plus a thin search endpoint that returns Markdown. JS-rendered pages are unreadable to the documented fetch tools, `llms.txt` is cheap but almost never fetched, and shipped embeddings tie readers to the publisher's model, so keep vector search behind the publisher's endpoint. The eval that would settle the format question (hold the agent fixed, vary the site) appears unoccupied and is cheap to build. Inbound, treat every message as tainted data: schema-validated intake, a quarantined parser, and no agent that both reads strangers' text and holds secrets or outbound tools. The signed-traffic idea does not hold up as stated: as of October 2026 Anthropic documents no request signing for any of its agent traffic, a signature attests infrastructure rather than content or classifier approval, and signed spam would most likely be an ordinary user instruction, not a jailbreak. LLM reviewers are useful checkers and poor judges of significance, and the observation that cross-model review catches more than self-review has good indirect support but no direct test.

**Top recommendation:** publish a git-native Markdown corpus with an index page, per-page `.md` URLs, a signed tarball and manifest, a `corpus.db` FTS5 file, and a `/search` endpoint that returns Markdown with absolute links. Then run the format-by-agent navigability eval in Section 9 before investing in anything fancier.

| Question | Short answer | Evidence strength |
| --- | --- | --- |
| SOTA for getting info into agents | Small high-signal context, an always-loaded index, just-in-time grep/fetch; embeddings as an add-on for large or fuzzy corpora | Measured (several studies), plus vendor claims |
| Best publishing form | Git repo of Markdown, served as static `.md` + index + tarball | Documented fetch-tool behavior; format-versus-task-success never measured |
| Agent site search | Index pages, then FTS5 file (shell), then Markdown `/search` (fetch-only), then optional MCP | Documented mechanics; agent use unmeasured |
| Evals | Benchmarks vary the retriever or the live site, never the format of a fixed corpus | Gap looks real |
| Signed traffic as moderation | An attribution and cost filter, not a content filter; excludes essentially all Claude traffic today | Documented specs and vendor pages |
| Cross-model review | Plausible and mechanistically supported; not directly tested | Indirect, measured |

Next section: https://ai.hiina.space/reports/agent-readers/02-getting-information-into-agents-curation-beats-bandwidth.md

---

Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space