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 specialagentgit 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/specialagent)<a href="https://agentmods.dev/skills/monoes/monomind/specialagent"><img src="https://agentmods.dev/badge/skills/monoes/monomind/specialagent/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/specialagent"><img src="https://agentmods.dev/badge/skills/monoes/monomind/specialagent.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 | $0.00051 | $0.00982 |
| Opus 5.5 | $0.00020 | $0.00393 |
| Sonnet 5.5 | $0.00010 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
specialagent 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/specialagent — Best Agent for a Task
Finds the best installed agent for a task. Never recommend from memory or from a hardcoded roster: the agent set differs per install, and a subagent_type that is not installed fails at spawn time.
Step 1: Use the pick index
In this order, stop at the first that answers:
[PICK]line — if the prompt carries[PICK] agent: <name> · skill: <invoke>, recommend that agent unless it is clearly wrong for the task.mcp__monomind__pick({ task: "<task>", kind: "agents", top: 5 })— choose the best fit amongagents.ranked[](prefer the top entry unless another is clearly more specific). Eachnameis a spawnablesubagent_type.- Local CLI —
monomind pick -t "<task>" --top 5 --json | jq -r '.agents.ranked[].name'(local binary only, never npx; seemastermind-agent-select/SKILL.mdfor the version-checkedmmpickhelper).
Step 2 (fallback): Two-stage domain → agent selection
Only when Step 1 returned nothing. Only names are passed at each stage — no descriptions, no keyword dumps.
Stage 1: Give LLM the category names → LLM picks the best category
Stage 2: Give LLM the agent names installed in that category → LLM picks the best agent
Categories are the .claude/agents/ folder names: architecture consensus core design engineering github goal marketing monoswarm optimization specialists specialized templates testing.
List the installed agent names in a category from the registry (or the definitions on disk):
CAT="engineering"
jq -r --arg c "$CAT" '.agents[] | select(.category == $c and .deprecated != true) | .name' .monomind/registry.json 2>/dev/null \
|| grep -h -m1 "^name:" packages/@monomind/cli/.claude/agents/$CAT/*.md .claude/agents/$CAT/*.md 2>/dev/null | sed 's/^name: *//'
Stage 1 prompt to yourself:
"Given the task:
<task>— which single category from this list best fits:<category names>? Answer with just the category name."
Stage 2 prompt to yourself:
"Given the task:
<task>— which single agent from this category is the best fit:<agent names listed above>? Answer with just the agent name."
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 · 86 lines · 51 tokens per session scan A 0598c632548f
specialagent is a skill published in the GitHub repository monoes/monomind (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 982 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
compare-harnesses
Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.
create-harness
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…
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.
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…
oia-manifest
Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.
repo-genome
7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.