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-invite-landinggit 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-invite-landing)<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-invite-landing"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-invite-landing/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-invite-landing"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-invite-landing.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 | $0.00039 | $0.02542 |
| Opus 5.5 | $0.00016 | $0.01017 |
| Sonnet 5.5 | $0.00008 | $0.00508 |
| Haiku 4.5 | $0.00004 | $0.00254 |
Grade A, and why
mastermind-invite-landing 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Invite Landing
This skill is invoked directly via /mastermind-invite-landing.
Bookkeeping only — not enforced by the Org Runtime. It writes .monomind/orgs/<org>-members.json, which no runtime code reads: joining grants no access. An agent join also appends a role stub to the org definition — check it with monomind org validate before running the org.
Inputs
brain_context: BRAIN CONTEXT block (injected by command, or loaded below if standalone)action: show | accept-human | accept-agent | statustoken: invite token (required; extract from monomind://invite?... URL or share link)org_name: org name (required unless extractable from token record)join_as: human | agent (for accept actions; default: agent in CLI context)display_name: human display name (for accept-human)email: email address (for accept-human)agent_name: agent display name (for accept-agent)adapter_type: claude-local | gemini-local | codex-local | cursor | opencode | hermes | http | acpx (for accept-agent; default: claude-local)model: model override (for accept-agent; uses adapter default if omitted)caller: command | master
Join Modes
| Mode | Who | Required Fields |
|---|---|---|
human |
A human operator joining the org | display_name, email |
agent |
An AI agent joining the org | agent_name, adapter_type |
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 — Validate Token
[ -z "$token" ] && { echo "ERROR: --token required. Extract from invite URL: monomind://invite?org=...&token=...&role=..."; exit 1; }
# Try to find org from token if org_name not given
if [ -z "$org_name" ]; then
# Search all members files for a matching invite token
for mf in .monomind/orgs/*-members.json; do
[ -f "$mf" ] || continue
match=$(jq -r --arg t "$token" '(.join_requests // [])[] | select(.token == $t or .id == $t) | .id' "$mf" 2>/dev/null | head -1)
if [ -n "$match" ]; then
org_name=$(basename "$mf" "-members.json")
break
fi
done
[ -z "$org_name" ] && { echo "ERROR: Could not find org for token '$token'. Specify --org-name explicitly."; exit 1; }
fi
membersFile=".monomind/orgs/${org_name}-members.json"
[ ! -f "$membersFile" ] && { echo "ERROR: Org '$org_name' members file not found."; exit 1; }
inviteDef=$(jq -r --arg t "$token" \
'(.join_requests // [])[] | select((.token == $t or .id == $t) and .type == "invite")' \
"$membersFile" | head -c 4096)
[ -z "$inviteDef" ] && { echo "ERROR: Invite token '$token' not found or already used."; exit 1; }
inviteStatus=$(echo "$inviteDef" | jq -r '.status // "pending"')
inviteRole=$(echo "$inviteDef" | jq -r '.role // "operator"')
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 · 231 lines · 39 tokens per session scan A 1060bc4b56a1
mastermind-invite-landing is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 2,542 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.