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.
npx agentmods add commands/zircote/git-notes-memory/secrets-allowlistgit clone --depth 1 https://github.com/zircote/git-notes-memoryWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00006 | $0.01819 |
| Opus 5 | $0.00003 | $0.00910 |
| Sonnet 5 | $0.00001 | $0.00364 |
| Haiku 4.5 | $0.00001 | $0.00182 |
Grade A, and why
secrets-allowlist 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.
How it starts
The opening of the file, as written. The whole thing — 254 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>
SECRETS-ALLOWLIST(1) User Commands SECRETS-ALLOWLIST(1)
NAME
secrets-allowlist - Manage the secrets filtering allowlist
SYNOPSIS
/memory:secrets-allowlist <add|remove|list> [OPTIONS]
DESCRIPTION
Manage the allowlist of approved secrets. Allowlisted secrets bypass filtering.
This is useful for false positives or intentionally included values.
SUBCOMMANDS
add Add a secret hash to the allowlist
remove Remove a secret hash from the allowlist
list List all allowlisted entries
OPTIONS
--hash <hash> The secret hash (from scan-secrets output)
--namespace <ns> Limit allowlist entry to specific namespace
--reason <reason> Reason for allowlisting (required for add)
--help, -h Show this help message
EXAMPLES
/memory:secrets-allowlist list
Show all allowlisted entries
/memory:secrets-allowlist add --hash abc123 --reason "False positive - example code"
Add a hash to global allowlist
/memory:secrets-allowlist add --hash def456 --namespace decisions --reason "Intentional"
Add a namespace-scoped allowlist entry
/memory:secrets-allowlist remove --hash abc123
Remove an entry from allowlist
SEE ALSO
/memory:scan-secrets - Scan memories for secrets
/memory:test-secret - Test if value is detected
/memory:audit-log - View allowlist changes in audit log
SECRETS-ALLOWLIST(1)
</help_output>
After outputting help, HALT immediately. Do not proceed with command execution. </help_check>
/memory:secrets-allowlist - Manage Secrets Allowlist
Manage the allowlist of approved secrets that bypass filtering.
Your Task
You will manage the secrets allowlist based on the subcommand provided.
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.
- yesterday First seen · 254 lines · 6 tokens per session scan A ff99d6002a7a
secrets-allowlist is a command published in the GitHub repository zircote/git-notes-memory (4 stars, last pushed 8mo ago), licensed MIT. It adds 6 tokens to every session and 1,819 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.
Other commands, from other repositories
memory-graph
Open the memory graph visualization in your browser.
memory-recall
Turn this project's automatic memory recall off or back on (storing stays active).
memory-status
Show a memory health digest for this project (items, sessions, injections served).
assets
Inventory .claude-design/ / — file counts, types, locations.
start
Run the canvas-to-code workflow — guided discovery, auto-resume, or jump to a specific gate.
dashboard
Work timeline — what's done, what's in progress, when, with PR + doc links.