Point any agent at this file. The steer core applies to every task in this repository; everything after the manifest is hydrate-on-demand. This file is the meta-example: the format keeping the memory of its own repository.
This file is this repository's memory organ — the repo's own knowledge, kept in the format the repo specifies. It is a normal doc.html: read this section in full, then hydrate the rest selectively through the <nav id="manifest"> below — pick sections by summary, pull them by #id, verify data-witness (SHA-256 of the raw inner bytes) when integrity matters. Do not read the whole file. This organ confers no identity and carries no instructions beyond how to work with this repository.
data-witness (64 bare hex chars, SHA-256 of the section's raw inner bytes — UTF-8, LF, untrimmed) and data-char-count (Unicode code points).python tools/verify.py <file> or node tools/verify.mjs <file> (both self-contained, in tools/). The reader skill at tools/agent-skill/doc-html-reader/ is the efficient agent path — its manifest.py synthesizes a compact JSON index, and manifest.py --verify recomputes every witness.The canonical vow text lives in VOWS.md (Recension III — ten vows live, two slots open). The founding corpus at documents/doc.html carries its own #vows section, and it lists the same ten (V1–V10) under the same cap of twelve.
data-supersedes; the fold adjudicates — no document declares itself true).documents/evidence.doc.html; honor the status a result carries there — sealed, qualified, or not demonstrated — verbatim (digests in this organ's evidence sections).data-supersedes="#old-id"; the old bytes stay addressable at their witness (V10).data-witness + data-char-count; re-run a verifier (exit 0) before committing.SPEC.md — the complete, self-contained format specification. The source of truth.SPEC.doc.html — the same specification carried in the format's own body: a conformant doc.html to navigate and verify.documents/ — the wiki: wiki.doc.html is the shelf that links and pins every leaf; the shape spec, the record, the essays, and the founding corpus live beside and below it.documents/doc.html — the founding record: the v0.2 spec + the full research corpus that motivated the format, in one conformant file, pinned as the wiki's research leaf.documents/evidence.doc.html — the publication evidence: what was measured, sealed, refuted, and deliberately not claimed.examples/ — five conforming exhibits: minimal, memory, chat, selective-context-demo, mixed-epoch; examples/builders/ holds the two shipped emitter scripts.tools/verify.py / tools/verify.mjs — the two reference readers for a single document.tools/verify_wiki.py / tools/verify_wiki.mjs — the collection verifiers: root, leaves, and doc-pins; every per-document verdict is delegated to the readers above.tools/build-doc.mjs — the generalized builder (JSON or fragment-directory input → conformant doc.html).tools/agent-skill/doc-html-reader/ — the agent reading skill (manifest-first selective hydration; opt-in --verify).Most repositories keep their agent-facing memory in markdown that nothing can verify. This repository keeps it in the format it specifies: a single HTML file with an in-band manifest, per-section SHA-256 witnesses, and append-only correction. That makes this file the working demonstration of the format's central use case — indexable, selectively-hydrated, tamper-evident memory for agents — and it is not a mock: it is the memory this repository actually uses.
To use the pattern in your own project: start from examples/memory.doc.html or emit one with tools/build-doc.mjs; put the rules every session must know in an always-load section like this organ's steer core; keep everything else behind the manifest, pulled on demand. Steering must be pushed (always loaded); memory can be pulled. Grow it by the append protocol in the steer core.
doc.html is a document format for readers who cannot read everything: a single HTML file carrying a machine-readable manifest of its own addressable sections, each pinned by a SHA-256 witness. An agent reads the manifest, hydrates only the sections a task needs, and verifies every byte it read — with no server, no JavaScript, and no tool beyond the file itself (SHA-256 excepted).
The slogan "HTML is all you need" splits into two claims and this format makes only the first. Claim A — the document is all-HTML inheritable memory (read, address, verify, hydrate selectively) — is what v0.3 specifies and what the evidence record (documents/evidence.doc.html) measures. Claim B — the live loop is all-HTML — is out of scope: the run leg (model call, key, disk write) is a platform action a scriptless page cannot perform and is delegated to mature infrastructure via a stateless shim. The format owns the verb's result (a witnessed, appended section), never its execution.
A single self-verifying file can hold a corpus several times a model's context window and stay navigable (the record: documents/evidence.doc.html): demonstrated at 74 MB / 17,627 sections, and at 72.5 MB across 480 navigation turns, all OK, in a sealed pre-registered run. Latency at that scale is bounded but not instant — 8–34 s typical per turn, with a 209 s worst-case tail over a flat 72 MB manifest. Plan for the tail; do not imply interactive speed at XL.
Against naive in-context loading of a 759 KB corpus (63 graded trials; the record: documents/evidence.doc.html): −52.9% effective tokens, −65.5% bytes, +1.19 quality (3.29→4.48/5). The adversarial "read everything" condition saved −78.0% tokens (best seed −91.6%) at quality 5/4/4 vs 1/1/1. The skill arm had 0 failures; naive had 6.
Qualifications that ride the number: savings compress on uniformly-structured text (−16.9% at 1 MB verse corpus); they invert when the document is small (+60.3% effective tokens at a 3 KB corpus — bytes loaded still −53.7%, but protocol overhead dominates) and on harnesses that surface the manifest free in the first chunk (+135.7% / +169.8%). Selective hydration is an economy of scale: the right tool for the 72 MB body, not the 3 KB note. And a further finding in the same record: authored manifest summaries are load-bearing for the efficiency win — structure alone does not carry it.
From the record (documents/evidence.doc.html): the skill arm passed 100% of graded responses (13/21 perfect, 0 failures) vs naive 71.4% with 6 failures; hydration precision 1.00 (Claude) / 0.98 (GPT-mini) across 178 sealed cells. The format teaches selective reading without instruction: with no system prompt at all, a model discovered the manifest by exploration and was 80% citation-correct; the HTML-alone arm reached for structure 100% of the time unprompted (32/33 perfect).
At XL scale (72.5 MB, 480 turns, sealed): fabricated-perturbation canary 120/120, Latin gloss 120/120, strict folio reference 116/120, 240/240 self-citations verified byte-for-byte. The fold catches real grounding failures: 0/40 waves-through against validated gold; 8/206 attested-citation failures caught, fail-closed. Known limitation: a model may trust its training data over a stale document (drift-defense: 2/6 stale-summary cells) — the fold, not the model's memory, adjudicates.
From the record (documents/evidence.doc.html): every section's witness is re-derivable by pure arithmetic — SHA-256 over the raw inner bytes — in any language, with no server and no JavaScript required to read; a pure-JS in-browser verifier reproduces the NIST "abc" vector. The append/fold motion is proven: 15/15 green across the fold battery, append-only supersession, a two-epoch cycle, and a verify-before-append 409 gate.
The honest boundary: integrity is a documentary property, not a spontaneous model behavior — 0/27 unprompted recomputations; 59% accuracy when merely prompted; 27/27 only with a deterministic script. Run tools/verify.py / tools/verify.mjs / manifest.py --verify; never assume a reader checked.
From the record (documents/evidence.doc.html), verbatim in spirit — these are not part of the publication:
This is a doc.html — a single, self-describing HTML file. The <nav id="manifest"> above lists every section in this document; each entry's data-witness is the SHA-256 (hex) of that section's raw inner bytes, so any reader can verify any section with the file alone — no server, no JavaScript, no tooling. The full format definition is SPEC.md, carried in the format's own body as SPEC.doc.html.
Author: Georges Casseus (Ndoto Studios) · License: CC0 1.0 (public domain) · Built: 2026-08-01