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/hjqcan/goodmemory/tracegit clone --depth 1 https://github.com/hjqcan/GoodMemoryWhat 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 | $0.00009 | $0.00108 |
| Opus 5 | $0.00005 | $0.00054 |
| Sonnet 5 | $0.00002 | $0.00022 |
| Haiku 4.5 | $0.00001 | $0.00011 |
Grade A, and why
trace 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.
What it actually says
Call mcp__goodmemory__goodmemory_trace_recall with query set to
$ARGUMENTS, retrievalProfile set to coding_agent, and cwd set to the
current project absolute path. Summarize routing, hits, scores, and suppression
reasons without presenting the trace as proof that a memory is true. If
$ARGUMENTS is empty, ask for the query to diagnose.
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.
- 2d ago First seen · 10 lines · 9 tokens per session scan A 0eb8ebf1f87f
trace is a command published in the GitHub repository hjqcan/GoodMemory (17 stars, last pushed 10d ago), licensed MIT. It adds 9 tokens to every session and 108 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 2026-08-30.
Other commands, from other repositories
krimto-status
Show the current state of Krimto memory — total facts, scope breakdown, recent writes, and index health.
memory-check
Validate INTERNALRAG (index + validate + status + guard).
checkpoint
Persist current implementation state.
memory
Start or resume a task with INTERNALRAG.
memory-guard
Verify checkpoint freshness.
fix
Universal debugging and fix application with semantic code analysis.