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/tracesgit 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 | $0.00986 |
| Opus 5 | $0.00003 | $0.00493 |
| Sonnet 5 | $0.00001 | $0.00197 |
| Haiku 4.5 | $0.00001 | $0.00099 |
Grade A, and why
traces 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 — 147 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>
TRACES(1) User Commands TRACES(1)
NAME
traces - Display recent trace spans for debugging
SYNOPSIS
/memory:traces [--operation=<name>] [--status=ok|error] [--limit=<n>]
DESCRIPTION
Display completed trace spans from memory operations. Useful for debugging
performance issues and understanding operation flow. Shows timing, status,
and context for each traced operation.
OPTIONS
--help, -h Show this help message
--operation=NAME Filter by operation name (e.g., "capture", "recall")
--status=STATUS Filter by status: ok, error
--limit=N Maximum traces to show (default: 10)
EXAMPLES
/memory:traces
/memory:traces --limit=20
/memory:traces --operation=capture
/memory:traces --status=error
/memory:traces --operation=recall --limit=5
/memory:traces --help
SEE ALSO
/memory:metrics for collected metrics
/memory:health for health status with timing
TRACES(1)
</help_output>
After outputting help, HALT immediately. Do not proceed with command execution. </help_check>
/memory:traces - Recent Trace Spans
Display recent trace spans for debugging memory operations.
Your Task
You will display completed traces from the observability system.
Arguments format: $ARGUMENTS
Parse the following options:
--operation=<name>- Filter by operation name--status=ok|error- Filter by status--limit=<n>- Maximum traces to show (default: 10)
Execute the traces collection:
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-$(ls -d ~/.claude/plugins/cache/git-notes-memory/memory-capture/*/ 2>/dev/null | head -1)}"
uv run --directory "$PLUGIN_ROOT" python3 "$PLUGIN_ROOT/scripts/traces.py" $ARGUMENTS
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 · 147 lines · 6 tokens per session scan A 563e4952fbf3
traces 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 986 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.