audit

A command-line viewer for the history of memory-store operations, such as reading, writing, and recalling data.

In plain words
What is it for?
Use it to inspect recent activity, filter audit entries, limit the results, or export the raw entries as JSON.
Why use it?
It shows what happened in the central database and lets you narrow the history by time or operation.

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/audit
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 380 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 $0.00380
Opus 5 $0.00000 $0.00190
Sonnet 5 $0.00000 $0.00076
Haiku 4.5 $0.00000 $0.00038

Measured 2d ago against content hash f17bbdc6f894, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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/audit.md · 60 lines

What it actually says

gnosys audit

View the structured audit trail of memory operations from the central DB.

Usage

gnosys audit
gnosys audit --days 30
gnosys audit --operation write
gnosys audit --limit 50
gnosys audit --json

Options

Option Description
--days <n> Show entries from the last N days (default: 7)
--operation <op> Filter by operation type (read, write, recall, dream_*, etc.)
--limit <n> Maximum entries to return
--json Output raw JSON instead of formatted timeline

Behavior

  1. Opens the central DB via GnosysDB.openCentral().
  2. Reads audit entries with readAuditFromDb(centralDb, { days, operation, limit }).
  3. Prints formatAuditTimeline(entries) or JSON.
  4. Closes central DB in finally.

Output modes

Formatted timeline (default): human-readable operation history.

JSON (--json): raw entry array via JSON.stringify(entries, null, 2).

Errors

Central DB unavailable:

Central DB unavailable.

Exits with code 1 via process.exitCode after closing the DB handle in finally.

Validation

cd gnosys-public
npm run cli -- audit --help
npx vitest run src/test/audit-command-handler.test.ts
  • gnosys history — per-memory change history.
  • gnosys dream log — dream run audit subset.
  • gnosys sync — push/pull central DB including audit entries.
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 · 60 lines · 0 tokens per session scan A f17bbdc6f894

Subscribe to this mod's changes

audit is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 380 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.