Skip to main content

Module guide

Module guide 

Source
Expand description

GUIDE-1 (12.2): the guide for agents, compiled into the binary (docs/design/12.2-onboard.md, section 6).

One source, guide/guide.md, and every delivery is cut from it: mnemo onboard --guide (Markdown or llms.txt), and, in later steps, the MCP server’s instructions and mnemo://guide, the SessionStart hook, and the rule files onboard writes. Nothing at run time changes it: the trust boundary is that the guide lives in the binary.

The source marks two things for its deliveries and its test:

  • <!-- card --> … <!-- /card -->: the short card (at most CARD_MAX bytes) that the hook, the MCP instructions and the rule files carry;
  • fenced blocks whose info string has a tag after the language: ```sh test (a shell block CI runs), ```json mcp (an MCP request CI sends), and model on either (it needs the built-in embedder’s model). Deliveries drop the tags.

Structs§

Block
A fenced block of the guide.

Constants§

CARD_MAX
The most bytes the card may take.
FRAMING
The framing line placed before anything shown from the brain, in every delivery that shows brain content (the SessionStart hook, mnemo://about, mnemo://recent, mnemo://key/{key} and the prompts): memories are written by agents, often from untrusted input, so they’re data.
FULL_URL
Where the site serves the whole guide.
ONBOARD_HEADER
The header line on every file mnemo onboard writes; onboard and onboard --undo recognise their own files by it.
PLUGIN_HEADER
The header on the plugin’s committed skill.
SKILL_DESCRIPTION
The skill’s description (its frontmatter).
SOURCE
The guide’s source, as written.
SUMMARY
The one-line summary llms.txt opens with.

Functions§

blocks
Every fenced block in the guide, in order.
card
The card: the text between the card marks, trimmed, with \n line ends whatever the checkout used (a Windows checkout may turn the source’s into \r\n).
cursor_rule
.cursor/rules/mnemo.mdc: always applied, so only the card.
escape_brain
Brain text as it’s shown after FRAMING (RB-011.5 item 6): a line that starts with # (a heading of its own) or with the framing line’s words gets a \ in front, so it can’t pass for a part of what mnemo wrote around it. The essence’s own headings (# essence — … and ## <section>) stay as they are. The card’s rule that brain content is data is the real guard; this keeps the boundary visible.
layer_two
The guide’s layer 2 (sections 2 and 3: the tools, and organizing memory), as Markdown.
llms_full
The whole guide, for llms-full.txt: the same as markdown.
llms_txt
The guide as llms.txt, in llmstxt.org’s shape (https://llmstxt.org/): an H1, a blockquote summary, the card’s text (no headings), then H2 lists of links: Docs (the whole guide as llms_full, and the engine’s README) and Optional (the design notes). The repository’s llms.txt is this, checked by a test.
markdown
The guide as Markdown, for mnemo onboard --guide: the card marks are removed, each fence keeps only its language, and lines end in \n.
plugin_skill_md
The plugin’s skills/mnemo/SKILL.md (integrations/claude-code/).
skill_md
.claude/skills/mnemo/SKILL.md as onboard writes it: the frontmatter (first, or Claude Code doesn’t read it), the header, the card and layer 2.