mastermind-inbox

mastermind-inbox is a skill for Claude Code, Codex from monoes/monomind. It costs 32 tokens per session (1,997 once invoked), scanned A, original, Apache-2.0.

A cross-organisation inbox for items that need human attention, such as approvals, running organisations, active assignments and budget alerts.

In plain words
What is it for?
Use it to read, filter, complete or archive approval requests, heartbeat items, tasks and alerts.
Why use it?
It gathers important operational items from multiple organisations instead of requiring separate checks for each one.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to read, filter, complete or archive approval requests, heartbeat items, tasks and alerts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/monoes/monomind/mastermind-inbox
Install

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.

Any agent
npx skills add monoes/monomind --skill mastermind-inbox
Clone the repo
git clone --depth 1 https://github.com/monoes/monomind

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for mastermind-inbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/monoes/monomind/mastermind-inbox/github.svg)](https://agentmods.dev/skills/monoes/monomind/mastermind-inbox)
Your own site
<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-inbox"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-inbox/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.

agentmods 80×15 button for mastermind-inbox

Your own site · 80×15
<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-inbox"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-inbox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,997 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.01997
Opus 5.5 $0.00013 $0.00799
Sonnet 5.5 $0.00006 $0.00399
Haiku 4.5 $0.00003 $0.00200

Measured 2d ago against content hash 40cac7be13d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mastermind-inbox 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.

.agents/skills/mastermind-inbox/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mastermind Inbox

This skill is invoked directly via /mastermind-inbox.


Inputs

  • brain_context: BRAIN CONTEXT block
  • org_name: optional — filter to a single org (default: all orgs)
  • filter: all | approvals | heartbeats | tasks | alerts (default: all)
  • action: read | mark-done | archive
  • item_id: id of item to action
  • 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 — Collect All 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

Step 2 — Gather Inbox Items

For each org, collect:

total_approvals=0
total_heartbeats=0
total_alerts=0

for org in $orgs; do
  orgFile=".monomind/orgs/${org}.json"
  stateFile=".monomind/orgs/${org}-state.json"
  approvalsFile=".monomind/orgs/${org}/approvals.json"
  rtFile=".monomind/orgs/${org}/runtime.json"

  # 1. Pending tool approvals (the runtime's queue — `monomind org approvals <org>`)
  if [ -f "$approvalsFile" ]; then
    pending=$(jq '[(.approvals // [])[] | select(.approved == null)] | length' "$approvalsFile" 2>/dev/null || echo 0)
    total_approvals=$((total_approvals + pending))
  fi

  # 2. Running orgs (runtime.json status "running" with a live pid)
  rt_pid=$(jq -r 'if .status == "running" then (.pid // 0) else 0 end' "$rtFile" 2>/dev/null || echo 0)
  if [ "$rt_pid" -gt 0 ] && kill -0 "$rt_pid" 2>/dev/null; then
    total_heartbeats=$((total_heartbeats + 1))
  fi

  # 3. Budget alerts
  budget=$(jq -r '.run_config.budget_tokens // 0' "$orgFile" 2>/dev/null || echo 0)
  threshold=$(jq -r '.run_config.alert_threshold // 0.8' "$orgFile" 2>/dev/null || echo 0.8)
  if [ "$budget" -gt 0 ] && [ -f "$stateFile" ]; then
    total_in=$(jq '[.agents // {} | to_entries[] | .value.tokens_in // 0] | add // 0' "$stateFile" 2>/dev/null || echo 0)
    total_out=$(jq '[.agents // {} | to_entries[] | .value.tokens_out // 0] | add // 0' "$stateFile" 2>/dev/null || echo 0)
    total_tok=$((total_in + total_out))
    over=$(awk -v t="$total_tok" -v b="$budget" -v thr="$threshold" \
      'BEGIN { print (b>0 && t/b >= thr) ? "yes" : "no" }')
    [ "$over" = "yes" ] && total_alerts=$((total_alerts + 1))
  fi
done

Read the full file on GitHub · 207 lines

Changes

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.

  1. 2d ago First seen · 207 lines · 32 tokens per session scan A 40cac7be13d6

Subscribe to this mod's changes

mastermind-inbox is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,997 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.

Related

Other skills, from other repositories

agent-swarm-issue

Agent skill for swarm-issue - invoke with $agent-swarm-issue.

ruvnet/ruflo · 21 tokens

agent-user-tools

Agent skill for user-tools - invoke with $agent-user-tools.

ruvnet/ruflo · 16 tokens

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…

mvschwarz/openrig · 94 tokens

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.

ruvnet/metaharness · 85 tokens

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.

ruvnet/metaharness · 0 tokens

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.

ruvnet/metaharness · 45 tokens