Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/modeled-information-format/mnemonicnpx agentmods add commands/modeled-information-format/mnemonic/queryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/modeled-information-format/mnemonic/query)<a href="https://agentmods.dev/commands/modeled-information-format/mnemonic/query"><img src="https://agentmods.dev/badge/commands/modeled-information-format/mnemonic/query/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/modeled-information-format/mnemonic/query"><img src="https://agentmods.dev/badge/commands/modeled-information-format/mnemonic/query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.01061 |
| Opus 5.5 | $0.00004 | $0.00424 |
| Sonnet 5.5 | $0.00002 | $0.00212 |
| Haiku 4.5 | $0.00001 | $0.00106 |
Grade A, and why
query 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Search first: /mnemonic:search {relevant_keywords}
Capture after: /mnemonic:capture {namespace} "{title}"
Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.
/mnemonic:query
Structured queries on memory frontmatter fields using yq for YAML parsing.
Arguments
--type- Filter by memory type (semantic, episodic, procedural)--namespace- Filter by namespace pattern (supports wildcards likedecisions/*)--tag- Filter by tag (can be specified multiple times)--confidence- Filter by confidence with operators (>, >=, <, <=, ..)--created- Filter by created date with operators--modified- Filter by modified date with operators--title- Filter by title pattern (regex)--scope- Limit to user, project, or all (default: all)--format- Output format: paths, titles, json, count (default: paths)--limit- Limit output to N results
Operators
| Operator | Example | Description |
|---|---|---|
= (implicit) |
--confidence 0.9 |
Exact match |
!= |
--type "!=episodic" |
Not equal |
> |
--confidence ">0.8" |
Greater than |
>= |
--confidence ">=0.9" |
Greater or equal |
< |
--confidence "<0.5" |
Less than |
<= |
--confidence "<=0.7" |
Less or equal |
.. |
--confidence "0.7..0.9" |
Range (inclusive) |
Procedure
Step 1: Check yq Installation
if ! command -v yq &>/dev/null; then
echo "Error: yq is required. Install: brew install yq"
exit 1
fi
Step 2: Execute Query
# Run mnemonic-query with provided arguments
./tools/mnemonic-query "$@"
Example Usage
# Find all semantic memories
/mnemonic:query --type semantic
# Find high-confidence memories
/mnemonic:query --confidence ">0.8"
# Find memories in confidence range
/mnemonic:query --confidence "0.5..0.9"
# Find by tag and type
/mnemonic:query --tag architecture --type semantic
# Find decisions with security tag
/mnemonic:query --namespace "_semantic/decisions" --tag security
# Exclude episodic memories
/mnemonic:query --type "!=episodic"
# Find memories created in date range
/mnemonic:query --created "2026-01-01..2026-01-31"
# Get count only
/mnemonic:query --type semantic --format count
# Get titles
/mnemonic:query --tag architecture --format titles
# Limit results
/mnemonic:query --type semantic --limit 10
# Pipe to content search
/mnemonic:query --tag security | xargs rg "password"
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.
- 1mo ago First seen · 158 lines · 9 tokens per session scan A 21c311a606e3
query is a command published in the GitHub repository modeled-information-format/mnemonic (23 stars, last pushed 3d ago), licensed MIT. It adds 9 tokens to every session and 1,061 once invoked, about $0.0000 per session on Opus 5.5. 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
dream-defrag
A command for pruning Claude Code’s saved memory files, including MEMORY.md and other memory notes.
context-preload
A command for managing and setting up ContextPreloader.
voice-refresh
Refresh the founder-voice DNA from new Granola meetings (interactive, MCP-backed). Pulls meetings since the last refresh, harvests Assaf-only speech, runs the Stage 2-3 orchestrator, and presents a founder-gated delta. Never auto-writes voice-dna.md.
q-research
Read the research-mode skill's SKILL.md for the full ruleset before proceeding. Follow all constraints, the source lookup cascade, the token budget, and the "what counts as cited" rules exactly.
status
Show memex statistics and status including projects, memos, and pending items.
learn
Command "learn" from datacore-one/datacore, covering /learn, purpose, when to use, usage and quick capture.