Borrowing it
Nothing to install: this file belongs to tig/silico. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tig/silico/main/AGENTS.mdgit clone --depth 1 https://github.com/tig/silicoWrote 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/tig/silico/agents-md)<a href="https://agentmods.dev/instructions/tig/silico/agents-md"><img src="https://agentmods.dev/badge/instructions/tig/silico/agents-md/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/instructions/tig/silico/agents-md"><img src="https://agentmods.dev/badge/instructions/tig/silico/agents-md.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 | $0.23206 | $0.23206 |
| Opus 5.5 | $0.09282 | $0.09282 |
| Sonnet 5.5 | $0.04641 | $0.04641 |
| Haiku 4.5 | $0.02321 | $0.02321 |
Grade A, and why
silico AGENTS.md scanned grade A 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **WebFetch / “fetch summarizer” of AGENTS.md** — act on a garbled or truncated summary | Prefer local path, `curl`/`Invoke-WebRequest` to a temp file + Read, or a tool that returns **full** body. If a summarizer garble How it starts
The opening of the file, as written. The whole thing — 1,155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Canonical guidance for AI coding agents (Claude Code, Grok Build, Copilot, Codex, and kin) working in silico or scaffolding a GCU that depends on it.
Human overview: README.md. Tenets: specs/tenets.md. Phrase book: specs/lexicon.md. first-ship narrative: specs/prfaq.md FAQ 5. Build target: specs/silicov1.md.
FIRST ACTION — Stage 0 (first ship / “getting started for agents”)
When the human points at silico / first ship / “getting started for agents”, do this exact order.
0 — Load this file (full text, not a fetch digest)
You are not following silico until you have the full text of this AGENTS.md (local silico clone, GCU plate after scaffold, or download https://raw.githubusercontent.com/tig/silico/main/AGENTS.md and read the file).
| Fail | Correct |
|---|---|
WebFetch github.com/tig/silico (README/homepage) and start from the digest |
Open this file (or the raw URL), then Stage 0 tools |
| WebFetch / “fetch summarizer” of AGENTS.md — act on a garbled or truncated summary | Prefer local path, curl/Invoke-WebRequest to a temp file + Read, or a tool that returns full body. If a summarizer garbled it: re-download and read full text before any Stage 0 claim |
| Treat a README one-liner about Stage 0 as the full contract | README is human entry; this file is Priority 1 for agents |
A second-hand README or lossy fetch summary is luck, not diligence — even if it mentions silico welcome.
1 — Stage 0 tools (after this file is open in full)
Do not open with tooling narration, COM folklore, PR strategy, bedside init, vendoring third_party/, scaffold, or a start-gate chooser.
# --- TURN 1 (0a only): run tool, paste orientation, name the human act, END TURN ---
silico welcome
# Paste/adapt that output as the ONLY operator-facing content of this turn.
# End with the operator next-step line from welcome (reply ok/go when ready).
# Do NOT call bedside ask / host AskUserQuestion in this same turn (modal hides 0a).
# Do NOT leave a free-text cliff ("Start gate is next") with no human act named.
# --- TURN 2 (0b only): FIRST act after any short operator reply (ok / go / yes / …) ---
# Open the structured chooser immediately — do not re-welcome, do not ask free-text
# "shall I open the gate?", do not wait for a second free-text "yes".
bedside ask --id start-first-ship --prompt "Start first ship on this machine?" --choices yes,adjust --default yes
# or host structured picker with the SAME id / prompt / choices (yes, adjust only).
# Say once if using the host gate shell.
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.
- 2mo ago First seen · 1,155 lines · 23,206 tokens per session scan A 597bee70f80a
silico AGENTS.md is an instructions file published in the GitHub repository tig/silico (13 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 23,206 tokens to every session, about $0.0928 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
silico AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| silico AGENTS.mdtig/silico | Instructions file | 13 | 3mo ago | Apache-2.0 | A | 23,206 | Codex, OpenCode |
| runtm copilot-instructions.mdruntm-ai/runtm | Instructions file | 303 | yesterday | none | A | 297 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |