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-activitygit 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-activity)<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-activity"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-activity/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-activity"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-activity.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 | $0.00040 | $0.01740 |
| Opus 5.5 | $0.00016 | $0.00696 |
| Sonnet 5.5 | $0.00008 | $0.00348 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
mastermind-activity 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Activity
This skill is invoked directly via /mastermind-activity.
Inputs
brain_context: BRAIN CONTEXT block (injected by command, or loaded below if standalone)org_name: org to query (required)action: list | filter | export | statsentity_type: issue | project | goal | agent | routine | all (default: all)actor_id: filter by agent or user id (optional)limit: max events to show (default: 50, max: 200)since: ISO timestamp — show events after this time (optional)output_file: file path to export JSONL (for export action)caller: command | master
Event Entity Types
| Type | Description |
|---|---|
issue |
Issue created, status changed, assigned, closed |
project |
Project created, updated, archived |
goal |
Goal created, progress updated, closed |
agent |
Agent started, stopped, errored, completed |
routine |
Routine triggered, run started, run completed |
approval |
Approval requested, approved, rejected |
workspace |
Workspace provisioned, teardown |
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 — Load Activity Log
orgFile=".monomind/orgs/${org_name}.json"
[ ! -f "$orgFile" ] && { echo "ERROR: Org '${org_name}' not found."; exit 1; }
activityFile=".monomind/orgs/${org_name}-activity.jsonl"
limit="${limit:-50}"
entityType="${entity_type:-all}"
Step 2 — Execute Action
list (default)
echo "ACTIVITY — org: $org_name"
echo " Filter: type=${entityType} limit=${limit}${actor_id:+ actor=${actor_id}}${since:+ since=${since}}"
echo "────────────────────────────────────────────────────────"
printf "%-20s %-12s %-14s %-24s %s\n" "TIMESTAMP" "ENTITY TYPE" "ACTOR" "ENTITY" "EVENT"
echo "────────────────────────────────────────────────────────"
if [ ! -f "$activityFile" ]; then
# Fall back to mastermind-events.jsonl
eventSrc="data/mastermind-events.jsonl"
if [ ! -f "$eventSrc" ]; then
echo " No activity log found. Activity is written when agents run."
exit 0
fi
activityFile="$eventSrc"
fi
tail -${limit} "$activityFile" | while IFS= read -r line; do
et=$(echo "$line" | jq -r '.entityType // .type // "unknown"')
actor=$(echo "$line" | jq -r '.actorId // .actor // "-"' | cut -c1-12)
entity=$(echo "$line" | jq -r '(.entityId // .entity // "-")' | cut -c1-22)
event=$(echo "$line" | jq -r '.event // .action // .type // "-"')
ts=$(echo "$line" | jq -r '.ts // .timestamp // .createdAt // "-"' | cut -c1-19)
# Apply filters
[ "$entityType" != "all" ] && [ "$et" != "$entityType" ] && continue
[ -n "$actor_id" ] && [ "$actor" != "$actor_id" ] && continue
[ -n "$since" ] && [ "$ts" \< "$since" ] && continue
printf "%-20s %-12s %-14s %-24s %s\n" "$ts" "$et" "$actor" "$entity" "$event"
done
echo ""
echo " Showing last $limit events. Use --limit N for more (max 200)."
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 · 193 lines · 40 tokens per session scan A 56e17c37cd31
mastermind-activity is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,740 once invoked, about $0.0002 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.