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/obidel/agentmemory/search-memoriesgit clone --depth 1 https://github.com/Obidel/AgentmemoryWhat 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 | $0.00011 | $0.00158 |
| Opus 5 | $0.00005 | $0.00079 |
| Sonnet 5 | $0.00002 | $0.00032 |
| Haiku 4.5 | $0.00001 | $0.00016 |
Grade A, and why
search-memories 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
Search the user's project memory via AgentMemory MCP.
Arguments:
- $1 (required): search query
- $2 (optional): project name
- $3 (optional): filter by category
- $4 (optional): max results (default 5)
Call:
mcp__agentmemory__search_memories({
query: "$1",
project_name: "$2" || undefined,
category: "$3" || undefined,
limit: parseInt("$4") || 5
})
Present the top results with their similarity scores, category badges, and created_at timestamps.
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 · 25 lines · 11 tokens per session scan A b8efb1264e20
search-memories is a command published in the GitHub repository Obidel/Agentmemory (2 stars, last pushed 3mo ago), licensed MIT. It adds 11 tokens to every session and 158 once invoked, about $0.0001 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
/spectra-propose
Create a complete change proposal with all artifacts in a single workflow.
/spectra-discuss
Have a focused discussion about a topic and reach a conclusion.
/spectra-ingest
Update an existing Spectra change from a plan file or conversation context.
/spectra-archive
Archive a completed change.
/spectra-debug
Systematically debug a problem using a four-phase workflow.
init-hooks
Initialize Blekline Codex hooks in this workspace.