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-environmentsgit 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-environments)<a href="https://agentmods.dev/skills/monoes/monomind/mastermind-environments"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-environments/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-environments"><img src="https://agentmods.dev/badge/skills/monoes/monomind/mastermind-environments.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 | $0.00042 | $0.02669 |
| Opus 5.5 | $0.00017 | $0.01068 |
| Sonnet 5.5 | $0.00008 | $0.00534 |
| Haiku 4.5 | $0.00004 | $0.00267 |
Grade A, and why
mastermind-environments 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mastermind Environments
This skill is invoked directly via /mastermind-environments.
Bookkeeping only — not enforced by the Org Runtime. It writes .monomind/orgs/<org>-environments.json, which no runtime code reads: creating an environment or changing the default does not change where agents run.
Inputs
brain_context: BRAIN CONTEXT block (injected by command, or loaded below if standalone)org_name: org to manage environments for (required)action: list | create | edit | delete | probe | set-defaultenv_id: environment id (required for edit/delete/probe/set-default)kind: local | ssh | sandbox (required for create)name: display name (required for create)host: SSH hostname or IP (required for ssh kind)port: SSH port (default 22)user: SSH username (required for ssh kind)secret_ref: secret name holding the SSH private key (see mastermind:secrets — NEVER pass raw key values)work_dir: remote working directory (default: /tmp/monomind)caller: command | master
Security Constraints
- NEVER print SSH private key values
- NEVER store key material in environment JSON files — store only the secret_ref name
- SSH keys must be stored via
mastermind:secretsand referenced by name only - Probe connection is read-only (runs
echo okover SSH)
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 Environments File
orgFile=".monomind/orgs/${org_name}.json"
[ ! -f "$orgFile" ] && { echo "ERROR: Org '${org_name}' not found."; exit 1; }
envFile=".monomind/orgs/${org_name}-environments.json"
[ ! -f "$envFile" ] && cat > "$envFile" <<'EOF'
{"environments":[],"default_env":null}
EOF
Step 2 — Execute Action
list (default)
echo "ENVIRONMENTS — org: $org_name"
echo "────────────────────────────────────────────────────────"
printf "%-20s %-10s %-28s %-8s %s\n" "ID" "KIND" "HOST / PATH" "DEFAULT" "SECRET REF"
echo "────────────────────────────────────────────────────────"
defaultEnv=$(jq -r '.default_env // "none"' "$envFile")
count=$(jq '.environments | length' "$envFile")
if [ "$count" -eq 0 ]; then
echo " No environments. Use --action create to add one."
else
jq -r --arg def "$defaultEnv" '(.environments // [])[] |
[
.id,
(.kind // "local"),
(if .kind == "ssh" then ((.user // "?") + "@" + (.host // "?") + ":" + ((.port // 22) | tostring)) else (.work_dir // "(local)") end),
(if .id == $def then "yes" else "-" end),
(.secret_ref // "-")
] | @tsv' "$envFile" | while IFS=$'\t' read -r id kind loc def sref; do
printf "%-20s %-10s %-28s %-8s %s\n" "$id" "$kind" "$loc" "$def" "$sref"
done
fi
echo ""
echo "Total: $count environment(s) | Default: $defaultEnv"
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 · 254 lines · 42 tokens per session scan A 7420b04be9bc
mastermind-environments is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 42 tokens to every session and 2,669 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
harness-secrets
GCP Secret Manager integration: validate setup, fetch values, or confirm an NPMTOKEN is non-revoked via npm whoami. Used for publish-time token rotation without long-lived keys in CI.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator.
flow-nexus-platform
Comprehensive Flow Nexus platform management - authentication, sandboxes, app deployment, payments, and challenges.
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…