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 pantheon-org/tekhne --skill design-agentsgit clone --depth 1 https://github.com/pantheon-org/tekhneWrote 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/pantheon-org/tekhne/design-agents)<a href="https://agentmods.dev/skills/pantheon-org/tekhne/design-agents"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/design-agents/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/pantheon-org/tekhne/design-agents"><img src="https://agentmods.dev/badge/skills/pantheon-org/tekhne/design-agents.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 | $0.00114 | $0.00981 |
| Opus 5 | $0.00057 | $0.00491 |
| Sonnet 5 | $0.00023 | $0.00196 |
| Haiku 4.5 | $0.00011 | $0.00098 |
Grade C, and why
opencode-design-agents scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
NEVER use `bash: { "*": "allow" }`. WHY: Allows destructive commands like `rm -rf`. Use `"*": "ask"` plus an explicit allowlist. How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Architect
Create and refine OpenCode agents through a guided Q&A process.
Quick Start
Create .opencode/agents/<name>.md:
---
description: Code review specialist. Use when user says "review", "check my code", "find bugs".
---
You are an expert code reviewer. Analyze code for bugs, security issues, and performance problems.
Provide specific, actionable feedback with line references.
For subagents (Task tool only), add mode: subagent. For permission restrictions, add a permission: block:
---
mode: subagent
permission:
bash:
"*": "ask"
"npm test": "allow"
---
Run bun run opencode and type /agents to confirm the new agent appears in the list.
Mindset
An agent is a markdown file with YAML frontmatter. Three decisions drive every design:
| Decision | Why it matters |
|---|---|
Scope (description) |
Controls when the agent triggers — too vague = never fires, too broad = fires on everything |
Mode (mode:) |
all = visible everywhere; subagent = Task-tool only; primary = main list only |
Permissions (permission:) |
Standard tools need no config; skills ALWAYS need explicit allowlists |
When to use: You need a distinct scope, persona, or permission set that differs from the default.
When NOT to use: Do not create an agent just to run a single command — use a slash command instead. Do not create a subagent when you just need a custom system prompt — use AGENTS.md.
Creation Workflow
Ask questions first. Follow phases in references/agent-patterns.md:
- Phase 1 — Core Purpose: What does it do? What triggers it? What persona?
- Phase 1.5 — Research: Look up current best practices for the domain.
- Phase 2 — Capabilities: Permissions, skills, mode (subagent vs primary vs all).
- Phase 3 — Review: Show draft, iterate until user approves.
Anti-Patterns
NEVER use bash: { "*": "allow" }. WHY: Allows destructive commands like rm -rf. Use "*": "ask" plus an explicit allowlist.
# BAD
permission:
bash:
"*": "allow"
# GOOD
permission:
bash:
"*": "ask"
"npm test": "allow"
"git status": "allow"
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .audits/2026-03-12/analysis.md 1.1 KB
- .audits/2026-03-12/audit.json 455 B
- .audits/2026-03-12/remediation-plan.md 3.0 KB
- .audits/2026-03-14/analysis.md 1.1 KB
- .audits/2026-03-14/audit.json 469 B
- .audits/2026-03-14/remediation-plan.md 3.2 KB
- .audits/2026-04-08/analysis.md 1.2 KB
- .audits/2026-04-08/audit.json 506 B
- .audits/latest 10 B
- .tessl-plugin/plugin.json 781 B
- CHANGELOG.md 1.2 KB
- evals/scenario-01.md 2.0 KB
- evals/scenario-02.md 1.6 KB
- evals/scenario-03.md 1.9 KB
- references/agent-patterns.md 8.7 KB
- references/opencode-config.md 5.3 KB
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.
- 8d ago First seen · 100 lines · 114 tokens per session scan C 869f3cb8c22a
opencode-design-agents is a skill published in the GitHub repository pantheon-org/tekhne (10 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 981 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
cf-validate
A validator for 1C configuration source files. It checks the XML structure and the files and objects that make up a 1C business-application configuration.
agent-code-generator
Generates Agent definitions (.md files) based on user intent and standard templates.