scan-secrets

A command that searches saved memories for secrets, such as credentials or private keys, and can apply configured cleanup rules.

In plain words
What is it for?
Use it to scan all memories or one namespace, review findings, preview cleanup, or remediate them.
Why use it?
It helps find sensitive information that may have been saved before secret filtering was enabled, while offering a dry run before changes are made.

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/zircote/git-notes-memory/scan-secrets
Clone the repo
git clone --depth 1 https://github.com/zircote/git-notes-memory
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,897 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 $0.00009 $0.01897
Opus 5 $0.00005 $0.00949
Sonnet 5 $0.00002 $0.00379
Haiku 4.5 $0.00001 $0.00190

Measured yesterday against content hash 54a8e8169236, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan-secrets 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 yesterday.

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.

commands/scan-secrets.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<help_check>

Help Check

If $ARGUMENTS contains --help or -h:

Output this help and HALT (do not proceed further):

<help_output>

SCAN-SECRETS(1)                                  User Commands                                  SCAN-SECRETS(1)

NAME
    scan-secrets - Scan existing memories for secrets and optionally remediate

SYNOPSIS
    /memory:scan-secrets [--namespace <ns>] [--fix] [--dry-run]

DESCRIPTION
    Scan memories for secrets that may have been captured before filtering was enabled.
    Reports findings without modifying memories unless --fix is specified.

OPTIONS
    --namespace <ns>      Only scan memories in this namespace
    --fix                 Apply configured filtering strategy to remediate secrets
    --dry-run             Show what would be changed without making changes
    --help, -h            Show this help message

EXAMPLES
    /memory:scan-secrets
        Scan all memories and report findings

    /memory:scan-secrets --namespace decisions
        Only scan the decisions namespace

    /memory:scan-secrets --fix --dry-run
        Show what remediation would do without changes

    /memory:scan-secrets --fix
        Apply remediation to all memories with secrets

SEE ALSO
    /memory:secrets-allowlist - Manage the secrets allowlist
    /memory:test-secret - Test if a value is detected as a secret
    /memory:audit-log - View secrets audit log

                                                                                              SCAN-SECRETS(1)

</help_output>

After outputting help, HALT immediately. Do not proceed with command execution. </help_check>


/memory:scan-secrets - Retrospective Secrets Scanner

Scan existing memories for secrets that may have been captured before filtering was enabled.

Your Task

You will scan memories for secrets and report findings, optionally remediating them.

Arguments format: $ARGUMENTS

Parse the following flags:

  • --namespace <ns>: Filter to specific namespace
  • --fix: Apply remediation (requires confirmation)
  • --dry-run: Show planned changes without executing

Read the full file on GitHub · 272 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. yesterday First seen · 272 lines · 9 tokens per session scan A 54a8e8169236

Subscribe to this mod's changes

scan-secrets is a command published in the GitHub repository zircote/git-notes-memory (4 stars, last pushed 8mo ago), licensed MIT. It adds 9 tokens to every session and 1,897 once invoked, about $0.0000 per session on Opus 5. 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.