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 skills add monoes/monomind --skill mastermind-searchgit clone --depth 1 https://github.com/monoes/monomindWrote 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/skills/monoes/monomind/mastermind-search)<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-search"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-search/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/skills/monoes/monomind/mastermind-search"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-search.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 | $0.00036 | $0.01948 |
| Opus 5.5 | $0.00014 | $0.00779 |
| Sonnet 5.5 | $0.00007 | $0.00390 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
mastermind-search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Search
This skill is invoked directly via /mastermind-search.
Inputs
brain_context: BRAIN CONTEXT block (injected by command, or loaded below if standalone)query: search term (required)org_name: filter to a specific org (optional — searches all orgs if omitted)scope: all | tasks | goals | agents | approvals | routines | projects | activity (default: all)limit: max results per category (default: 10)caller: command | master
Step 0 — Brain Load (standalone only)
If caller is not "command", load brain context following mastermind-protocol/SKILL.md Brain Load Procedure with namespace: ops.
Step 1 — Resolve Orgs
if [ -n "$org_name" ]; then
orgs="$org_name"
else
orgs=$(ls .monomind/orgs/*.json 2>/dev/null | grep -vE -- '-approvals|-state|-activity|-goals|-routines|-projects|-members|-issues|-workspaces|-worktrees|-environments|-plugins|-adapters|-bootstrap|-threads|-budgets|-project-workspaces|-approval-comments' | xargs -I{} basename {} .json | sort)
fi
[ -z "$orgs" ] && { echo "No orgs found. Run /mastermind:createorg first."; exit 0; }
Step 2 — Search All Scopes
query_lower=$(echo "$query" | tr '[:upper:]' '[:lower:]')
limit="${limit:-10}"
total_hits=0
echo "SEARCH: \"${query}\""
echo "════════════════════════════════════════════════"
echo ""
for org in $orgs; do
orgFile=".monomind/orgs/${org}.json"
[ ! -f "$orgFile" ] && continue
org_hits=0
# ── Agents ────────────────────────────────────────
if [ "$scope" = "all" ] || [ "$scope" = "agents" ]; then
hits=$(jq -r --arg q "$query_lower" \
'(.roles // [])[] | select((.id + " " + .title + " " + (.responsibilities // [] | join(" "))) | ascii_downcase | test($q)) |
"[AGENT] \(.id): \(.title) type=\(.agent_type)"' \
"$orgFile" 2>/dev/null | head -"$limit")
if [ -n "$hits" ]; then
echo "── $org / agents ──"
echo "$hits"
echo ""
org_hits=$((org_hits + $(echo "$hits" | wc -l)))
fi
fi
# ── Goals ─────────────────────────────────────────
goalsFile=".monomind/orgs/${org}-goals.json"
if [ -f "$goalsFile" ] && { [ "$scope" = "all" ] || [ "$scope" = "goals" ]; }; then
hits=$(jq -r --arg q "$query_lower" \
'(.goals // [])[] | select((.title + " " + (.description // "") + " " + (.status // "")) | ascii_downcase | test($q)) |
"[GOAL] [\(.id)] \(.title) status=\(.status // "open")"' \
"$goalsFile" 2>/dev/null | head -"$limit")
if [ -n "$hits" ]; then
echo "── $org / goals ──"
echo "$hits"
echo ""
org_hits=$((org_hits + $(echo "$hits" | wc -l)))
fi
fi
# ── Routines ──────────────────────────────────────
routinesFile=".monomind/orgs/${org}-routines.json"
if [ -f "$routinesFile" ] && { [ "$scope" = "all" ] || [ "$scope" = "routines" ]; }; then
hits=$(jq -r --arg q "$query_lower" \
'(.routines // [])[] | select((.name + " " + (.description // "") + " " + (.schedule // "")) | ascii_downcase | test($q)) |
"[ROUTINE] \(.name) schedule=\(.schedule // "-")"' \
"$routinesFile" 2>/dev/null | head -"$limit")
if [ -n "$hits" ]; then
echo "── $org / routines ──"
echo "$hits"
echo ""
org_hits=$((org_hits + $(echo "$hits" | wc -l)))
fi
fi
# ── Approvals ─────────────────────────────────────
approvalsFile=".monomind/orgs/${org}-approvals.json"
if [ -f "$approvalsFile" ] && { [ "$scope" = "all" ] || [ "$scope" = "approvals" ]; }; then
hits=$(jq -r --arg q "$query_lower" \
'(.approvals // [])[] | select((.title + " " + (.action // "") + " " + (.agent_id // "")) | ascii_downcase | test($q)) |
"[APPROVAL] [\(.id)] \(.agent_id): \(.title) status=\(.status)"' \
"$approvalsFile" 2>/dev/null | head -"$limit")
if [ -n "$hits" ]; then
echo "── $org / approvals ──"
echo "$hits"
echo ""
org_hits=$((org_hits + $(echo "$hits" | wc -l)))
fi
fi
# ── Projects ──────────────────────────────────────
projectsFile=".monomind/orgs/${org}-projects.json"
if [ -f "$projectsFile" ] && { [ "$scope" = "all" ] || [ "$scope" = "projects" ]; }; then
hits=$(jq -r --arg q "$query_lower" \
'(.projects // [])[] | select((.name + " " + (.description // "") + " " + (.lead // "")) | ascii_downcase | test($q)) |
"[PROJECT] \(.name) status=\(.status // "active") lead=\(.lead // "-")"' \
"$projectsFile" 2>/dev/null | head -"$limit")
if [ -n "$hits" ]; then
echo "── $org / projects ──"
echo "$hits"
echo ""
org_hits=$((org_hits + $(echo "$hits" | wc -l)))
fi
fi
# ── Activity log ──────────────────────────────────
if [ "$scope" = "all" ] || [ "$scope" = "activity" ]; then
eventsFile="data/mastermind-events.jsonl"
if [ -f "$eventsFile" ]; then
hits=$(grep "\"org\":\"$org\"" "$eventsFile" 2>/dev/null | \
jq -r --arg q "$query_lower" \
'select((tostring | ascii_downcase | test($q))) |
"[EVENT] \(.type) org=\(.org) \(if .task then "task=\(.task)" elif .role then "role=\(.role)" else "" end)"' \
2>/dev/null | tail -"$limit")
if [ -n "$hits" ]; then
echo "── $org / activity ──"
echo "$hits"
echo ""
org_hits=$((org_hits + $(echo "$hits" | wc -l)))
fi
fi
fi
total_hits=$((total_hits + org_hits))
done
if [ "$total_hits" -eq 0 ]; then
echo " No results found for \"${query}\""
echo ""
echo " Tips:"
echo " • Try a shorter or more general query"
echo " • Use --scope to narrow: tasks, goals, agents, approvals, routines, projects, activity"
echo " • Use --org to limit to a specific org"
fi
echo "════════════════════════════════════════════════"
echo "Found: ${total_hits} result(s)"
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 · 188 lines · 36 tokens per session scan A 0d8e1ac44c26
mastermind-search is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,948 once invoked, about $0.0001 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 2026-10-26.
Other skills, from other repositories
agent-swarm-issue
Agent skill for swarm-issue - invoke with $agent-swarm-issue.
agent-user-tools
Agent skill for user-tools - invoke with $agent-user-tools.
queue-handoff
Use when ending a turn, finishing a slice, blocked on another agent's work, or escalating to a human — durable work handoff via queue items so the system keeps moving across compactions, missed messages, and interruptions. Covers the hot-potato terminal-turn-rule (active work ends by passing the ball, not by going…
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
score-harness
5-dimension scorecard (0-100, grade A/B/C/F) for a scaffolded harness. Dimensions: Repo understanding (25%), Agent usefulness (25%), MCP safety (20%), Test coverage (15%), Publish readiness (15%). Emits a 6-field badges block (score + mcpRisk + 4 booleans) ready for the harness README. Exit 0 A/B, 1 C, 2 F.
verify-witness
Verify the Ed25519 witness manifest of a scaffolded harness. Fast yes/no signature check that proves the publisher signed this exact file set — separate from the full release-readiness umbrella in validate-harness.