search

95 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By modeled-information-format/mnemonic (GitHub) · coding · 23 stars · scanned at commit b13e26d

This skill should be used when the user says "search memories", "find in memories", "grep mnemonic", "look for memory", "deep search", "synthesize knowledge", or asks questions like "what do we know about X". Provides progressive disclosure and enhanced iterative search with synthesis.

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this. It runs automatically when the plugin is installed. Expected for a coding skill.

Found in 21 places.

skills/search/SKILL.md, line 42rg "^namespace: _semantic/decisions" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
skills/search/SKILL.md, line 49rg -l "^ - architecture" ${MNEMONIC_ROOT}/ --glob "*.memory.md"
skills/search/SKILL.md, line 58rg "^type: semantic" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l

Show 17 more

skills/search/SKILL.md, line 66rg "^created: 2026-01" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
skills/search/SKILL.md, line 72rg -i '^title: ".*auth.*"' ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
skills/search/SKILL.md, line 78rg "confidence: 0\.9" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
skills/search/SKILL.md, line 84rg -i "search term" ${MNEMONIC_ROOT}/ --glob "*.memory.md"
skills/search/SKILL.md, line 90rg "database" ${MNEMONIC_ROOT} --path "*/_semantic/decisions/" --glob "*.memory.md"
skills/search/SKILL.md, line 96find ${MNEMONIC_ROOT} -name "*.memory.md" -mtime -7
skills/search/SKILL.md, line 119qmd search "authentication middleware" -n 10
hooks/hooks.json, line 8"command": "${CLAUDE_PLUGIN_ROOT}/hooks/session_start.py",
hooks/hooks.json, line 20"command": "${CLAUDE_PLUGIN_ROOT}/hooks/pre_tool_use.py",
hooks/hooks.json, line 31"command": "${CLAUDE_PLUGIN_ROOT}/hooks/user_prompt_submit.py",
hooks/hooks.json, line 43"command": "${CLAUDE_PLUGIN_ROOT}/hooks/post_tool_use.py",
hooks/hooks.json, line 54"command": "${CLAUDE_PLUGIN_ROOT}/hooks/stop.py",
hooks/session_start.py, line 246git_check = subprocess.run(
hooks/session_start.py, line 253add_result = subprocess.run(
hooks/session_start.py, line 260subprocess.run(
hooks/stop.py, line 163result = subprocess.run(
hooks/stop.py, line 173subprocess.run(["git", "add", "-A"], cwd=str(mnemonic_path), timeout=5, capture_output=True)

and 1 more places

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'search' ] || [ -L ~/.agents/skills/'search' ]; then echo 'A skill folder named search already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/modeled-information-format/mnemonic' "$d" && git -C "$d" checkout --quiet 'b13e26d4431a89de2248db3ef390baeecc85cb2e' -- 'skills/search' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/search' ~/.agents/skills/'search' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'search' ~/.claude/skills/'search' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for modeled-information-format/mnemonic shows the score of its lowest-scoring skill.

SkillTrust badge for modeled-information-format/mnemonic

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/modeled-information-format/mnemonic.svg)](https://zalavijaysinh.github.io/skilltrust/repos/modeled-information-format/mnemonic/)

Score history

Date	Version	Score
2026-11-08	`b13e26d`	95