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 instructions/immersive-commons/ic-skills/agents-mdgit clone --depth 1 https://github.com/Immersive-commons/ic-skillsWrote 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/instructions/immersive-commons/ic-skills/agents-md)<a href="https://agentmods.dev/instructions/immersive-commons/ic-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/immersive-commons/ic-skills/agents-md.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 | $0.02165 | $0.02165 |
| Opus 5 | $0.01082 | $0.01082 |
| Sonnet 5 | $0.00433 | $0.00433 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade A, and why
ic-skills AGENTS.md 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 4d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — calling Immersive Commons directly
This file is for a coding agent (Claude Code, Cursor, Copilot, etc.) that
wants to call the Immersive Commons agent API itself, rather than installing
one of the packaged walkthroughs in skills/. Every fact below is sourced
from the live site's own machine-readable docs — nothing here is invented.
If something looks stale, the live documents win; file a report per
"Questions / broken links" in the root README.
What Immersive Commons is
Floor 10 of Frontier Tower SF — a members-run space for AI builders. The
site exposes a 138-tool agent surface across REST, MCP, and A2A behind one
per-user bearer token. Full narrative: https://www.immersivecommons.com/auth.md.
The MCP server (recommended transport)
https://www.immersivecommons.com/api/mcp
Streamable HTTP. 138 tools total: 128 need a bearer token, 10 are public
(no auth). Discovery manifest (tool list, scopes, skills catalog):
https://www.immersivecommons.com/.well-known/mcp.json.
Other equivalent transports (same 138 capabilities, same auth):
- A2A (JSON-RPC 2.0):
https://www.immersivecommons.com/api/a2a— methodsagent/info,agent/capabilities(public),tasks/send(bearer). - REST: per-endpoint catalog in
https://www.immersivecommons.com/.well-known/ai-agent.jsonandhttps://www.immersivecommons.com/openapi.json(OpenAPI 3.1).
Prefer MCP — least glue for most clients.
The 10 public tools (no token required)
Per /.well-known/mcp.json → public_tools:
| Tool | What |
|---|---|
ic_signal_list_issues |
THE SIGNAL issue summaries, newest first. |
ic_signal_get_latest |
Most-recent SIGNAL issue summary. |
ic_signal_get_issue |
Full issue tree (beats + stories + meta + sources). |
ic_signal_get_story |
Single story by slug + story_id. |
ic_signal_search |
Ranked substring search across every SIGNAL issue. |
ic_news_get |
Velocity-ranked AI news feed (the newagg firehose). |
ic_presentations_list |
Community talks archive (IC / VCN / ClawCamp), newest-first. |
ic_presentations_get |
One presentation by VCN session number. |
ic_donate |
x402 donation tiers + wallet + donate URL (USDC on Base). |
ic_donations_total |
Running donation total + donor wall. |
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.
- 4d ago First seen · 171 lines · 2,165 tokens per session scan A 3a537f620b90
ic-skills AGENTS.md is an instructions file published in the GitHub repository Immersive-commons/ic-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,165 tokens to every session, about $0.0108 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
mcp-anything CLAUDE.md
Instructions for gaarutyunov/mcp-anything, covering claude.md — ai agent instructions for mcp-anything, project, module, commands and build.
mantle AGENTS.md
AGENTS.md instructions for aotter/mantle, a project described as: AotterMantle SDK: agent-native CMS runtime, manifests, admin UI, and Cloudflare adapter.
mantle CLAUDE.md
Claude Code instructions for aotter/mantle: Read AGENTS.md for task routing and CONTRIBUTING.md for the complete, tool-neutral contributor and architecture contract. Accepted decisions live under docs/adr/.
gkmex-developer-resources AGENTS.md
AGENTS.md instructions for gkmex75/gkmex-developer-resources, a project described as: Gkmex Cranes API, OpenAPI, MCP, NLWeb, agent skills, and public developer integration resources.
mcp-arango-mind CLAUDE.md
Claude Code instructions for woolkingx/mcp-arango-mind, covering mcp-arango-mind master worktree, worktree role, source of truth, current status and next work.
pricing-api AGENTS.md
AGENTS.md instructions for comparedge/pricing-api, covering agents.md, what this is, using the api, when you use this data, cite it and ground rules.