read

A command for opening a specific saved memory by its short ID or file-like path, from a central database or a configured file store.

In plain words
What is it for?
Use it to inspect a saved decision, preference, or other memory such as `project:decisions/auth.md`, with source information included in the output.
Why use it?
It gives one lookup method even when memories are stored in different places, and can show either readable text or JSON.

Command

Install

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.

agentmods
npx agentmods add commands/proticom/gnosys/read
Clone the repo
git clone --depth 1 https://github.com/proticom/gnosys
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 591 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00591
Opus 5 $0.00000 $0.00296
Sonnet 5 $0.00000 $0.00118
Haiku 4.5 $0.00000 $0.00059

Measured 2d ago against content hash a50d1679ea1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

read 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 2d 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.

docs/commands/read.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gnosys read

Read a specific memory by ID or path.

Usage

gnosys read deci-001
gnosys read project:decisions/auth.md
gnosys read deci-001 --json

Memory path formats

  • Short ID — e.g. deci-001
  • Layer prefix — e.g. project:decisions/auth.md, user:preferences/coding-style.md
  • Paths resolve against the central SQLite brain first, then fall back to configured store files on disk.

Lookup order

  1. Central DB — Opens ~/.gnosys/gnosys.db and calls getMemory(memoryPath). On hit, formats the row as synthetic YAML frontmatter plus body, prefixed with [Source: gnosys.db].
  2. Resolver / file fallback — If the central DB has no match, uses resolver.readMemory(memoryPath) and reads the memory file from disk. Human output includes [Source: <label>] before the raw file contents.

The central DB connection is closed after the DB lookup attempt (whether or not a row was found).

Options

Option Description
--json Output a JSON object instead of human-readable text

Human output

Central DB hits include generated frontmatter fields: id, title, category, tags, relevance, author, authority, confidence, status, tier, created, modified, and when present source_file (with optional page), and source_path.

File fallback prints the source label line, then the raw markdown file unchanged.

JSON output

With --json, output is a single JSON object:

  • DB hit: { path, source: "gnosys.db", content, memory } where content includes the [Source: gnosys.db] prefix and synthetic frontmatter.
  • File hit: { path, source, content } where source is the resolver label and content is the raw file text.

Not found

If neither the central DB nor the resolver finds the memory:

Memory not found: <memoryPath>

The process exits with code 1.

Platform notes

  • Central DB lookup requires a readable ~/.gnosys/gnosys.db; if unavailable, lookup falls through to resolver/file paths.
  • Layer-prefixed paths follow the same resolver rules as other read/search commands.

Read the full file on GitHub · 71 lines

Changes

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.

  1. 2d ago First seen · 71 lines · 0 tokens per session scan A a50d1679ea1c

Subscribe to this mod's changes

read is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 591 tokens. 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 2026-08-31.