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 agentmods add skills/soemsakplus/pantheon/mainnpx skills add soemsakplus/pantheon --skill maingit clone --depth 1 https://github.com/soemsakplus/pantheonWrote 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/soemsakplus/pantheon/main)<a href="https://agentmods.dev/skills/soemsakplus/pantheon/main"><img src="https://agentmods.dev/badge/skills/soemsakplus/pantheon/main.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.06062 |
| Opus 5 | $0.00000 | $0.03031 |
| Sonnet 5 | $0.00000 | $0.01212 |
| Haiku 4.5 | $0.00000 | $0.00606 |
Grade A, and why
main 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 3d 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 — 457 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL.md — main
Capability layer. For identity see AGENT.md, for permissions see POLICY.md.
1. Tools
File system
- Read: anywhere in the repo
- Write:
agents/main/*+README.md+CLAUDE.md(other paths require L3)
Agent spawning (Task tool)
- Sub-agent (ephemeral, no MEMORY/POLICY) — spawn via Task tool, receive result directly
- Multi-agent invocation — read multi-agent's full 4-files, embed in Task prompt, spawn, receive result
External MCP / connectors
- Per root's authorization (Slack / Gmail / Calendar / etc.) — verify auth + scope before use
2. Skills
Skill 1: converse_with_root
Purpose: receive commands / answer / confirm / delegate
Flow:
- Receive input (CLI)
- Ambiguous → ask one consolidated clarifying question
- Routine + prior context → pull from MEMORY
- Decide: (a) answer self / (b) delegate multi-agent / (c) spawn sub-agent / (d) ask
- Reply per AGENT.md style
- Append summary to MEMORY
Skill 2: plan_task
Purpose: decompose request → assign agents
Flow:
- Understand goal + constraints
- Decompose to atomic sub-tasks
- Match agent (read AGENT/SKILL of candidates)
- Sequence dependencies / parallelize
- Output plan before execution
Pitfalls: Don't do it yourself when specialist exists. Don't over-decompose.
Skill 3: spawn_sub_agent
Purpose: create ephemeral agent for one-off task
Flow:
- Decide model (Haiku for cheap parsing, Sonnet for judgment)
- Construct system prompt with: role, parent (main), scope, tools allowed, exit condition, output format
- Invoke Task tool with the prompt
- Receive result directly from Task return — NO file-based inbox involved
- Process result; append decision to own MEMORY
Sub-agent system prompt template:
You are <role>, a sub-agent spawned by main.
You have NO long-term memory.
Task: <description>
Inputs: <list>
Tools allowed: <list>
Exit condition: <when to stop>
Output format: <format>
DEADLINE: <ISO timestamp> # if you can't finish by then, return STATUS: partial
EXPECTED_OUTPUT_FILE: <path> # optional — main verifies this file exists + non-empty
Comm rules:
- Don't talk to root directly.
- Don't contact other agents.
- Never write to any MEMORY file (you are stateless).
- Return your result to caller. Then exit.
Output MUST end with a status block:
STATUS: ok | partial | failed
ERROR_TYPE: <one of: auth_error | source_unreachable | parse_error | policy_block | internal_error | timeout | other> # required when partial or failed; omit when ok
REASON: <one short line — required when partial or failed>
What ships with it
8 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.
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.
- 3d ago First seen · 457 lines · 0 tokens per session scan A 3fd76b0507e4
main is a skill published in the GitHub repository soemsakplus/pantheon (2 stars, last pushed 3mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 6,062 tokens. 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…