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/modeled-information-format/mnemonic/searchgit clone --depth 1 https://github.com/modeled-information-format/mnemonicWhat 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 | $0.00008 | $0.01130 |
| Opus 5 | $0.00004 | $0.00565 |
| Sonnet 5 | $0.00002 | $0.00226 |
| Haiku 4.5 | $0.00001 | $0.00113 |
Grade A, and why
search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Search first: /mnemonic:search {relevant_keywords}
Capture after: /mnemonic:capture {namespace} "{title}"
Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.
/mnemonic:search
Direct ripgrep search across mnemonic memories.
Arguments
<pattern>- Required. Search pattern (supports regex)--namespace- Limit search to specific namespace--context- Lines of context around matches (default: 0)--files-only- Only list matching file paths--case-sensitive- Case-sensitive search (default: case-insensitive)--scope- user, project, or all (default: all)
Procedure
Step 1: Parse Arguments
PATTERN="${1:?Error: Pattern required}"
NAMESPACE="${NAMESPACE:-}"
CONTEXT="${CONTEXT:-0}"
FILES_ONLY="${FILES_ONLY:-false}"
CASE_SENSITIVE="${CASE_SENSITIVE:-false}"
SCOPE="${SCOPE:-all}"
ORG=$(git remote get-url origin 2>/dev/null | sed -E 's|.*[:/]([^/]+)/[^/]+\.git$|\1|' | sed 's|\.git$||')
[ -z "$ORG" ] && ORG="default"
Step 2: Build Search Command
# Base command
RG_CMD="rg"
# Case sensitivity
[ "$CASE_SENSITIVE" = "false" ] && RG_CMD="$RG_CMD -i"
# Context lines
[ "$CONTEXT" -gt 0 ] && RG_CMD="$RG_CMD -C$CONTEXT"
# Files only
[ "$FILES_ONLY" = "true" ] && RG_CMD="$RG_CMD -l"
# File pattern
RG_CMD="$RG_CMD --glob '*.memory.md'"
Step 3: Determine Search Paths
SEARCH_PATHS=""
case "$SCOPE" in
user)
SEARCH_PATHS="$HOME/.claude/mnemonic/$ORG"
;;
project)
SEARCH_PATHS="./.claude/mnemonic"
;;
all|*)
SEARCH_PATHS="$HOME/.claude/mnemonic/$ORG ./.claude/mnemonic"
;;
esac
# Narrow by namespace
if [ -n "$NAMESPACE" ]; then
NEW_PATHS=""
for path in $SEARCH_PATHS; do
[ -d "$path/$NAMESPACE" ] && NEW_PATHS="$NEW_PATHS $path/$NAMESPACE"
done
SEARCH_PATHS="$NEW_PATHS"
fi
Step 4: Execute Search
echo "=== Searching: $PATTERN ==="
echo ""
for path in $SEARCH_PATHS; do
if [ -d "$path" ]; then
if [ "$FILES_ONLY" = "true" ]; then
rg $([[ "$CASE_SENSITIVE" = "false" ]] && echo "-i") -l "$PATTERN" "$path" --glob "*.memory.md" 2>/dev/null
else
rg $([[ "$CASE_SENSITIVE" = "false" ]] && echo "-i") $([[ "$CONTEXT" -gt 0 ]] && echo "-C$CONTEXT") "$PATTERN" "$path" --glob "*.memory.md" 2>/dev/null
fi
fi
done
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 · 179 lines · 8 tokens per session scan A e88b114b6380
search is a command published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 1,130 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
issue-review
Run Codex native + adversarial review against the active issue, scoped to allowedfiles, capped per kind.
wiring-check
End-of-task wiring gate — verify every change is connected end-to-end across kipi plugins, hooks, MCP tools, agents, bus files, canonical, and rules. Nothing dangling.
issue-closeout
Triage Codex findings via per-finding dispositions, record findingstriaged, close the active issue.
prd-personas
Run the Skeptic persona session against the active draft PRD.
linear-drain
Create the queued Linear projects and issues that shell scripts captured offline.
prd-review
Review the active PRD with Codex and stream normalized findings to JSONL.