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/cote-star/agent-context/gemini-mdgit clone --depth 1 https://github.com/cote-star/agent-contextWhat 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 | $0.00097 | $0.00097 |
| Opus 5 | $0.00048 | $0.00048 |
| Sonnet 5 | $0.00019 | $0.00019 |
| Haiku 4.5 | $0.00010 | $0.00010 |
Grade A, and why
agent-context GEMINI.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 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.
This is a copy
100% identical to agent-context CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
BEFORE starting any task, read these 3 files in order:
- .agent-context/current/00_START_HERE.md
- .agent-context/current/30_BEHAVIORAL_INVARIANTS.md
- .agent-context/current/20_CODE_MAP.md Do NOT open repo source files until steps 1-3 are complete. Then open only files .agent-context identifies as relevant to your task.
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 · 9 lines · 97 tokens per session scan A 1bac235ea024
agent-context GEMINI.md is an instructions file published in the GitHub repository cote-star/agent-context (2 stars, last pushed 2mo ago), licensed MIT. It adds 97 tokens to every session, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-context CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
vitaecontext AGENTS.md
AGENTS.md instructions for vitaecontext/vitaecontext, covering agents.md, scope, start here, source of truth and brand contract.
vitaecontext copilot-instructions.md
Copilot instructions for vitaecontext/vitaecontext, covering repository instructions for github copilot, repository model, coding and documentation rules and validation.
vitaecontext GEMINI.md
Gemini CLI instructions for vitaecontext/vitaecontext, covering vitaecontext, module map and runtime loading.
okp AGENTS.md
Instructions for talesofai/okp, covering agents.md — project conventions for okp, tech stack, architecture, api 端点 and data model (postgresql).
project-tiny-context-harness AGENTS.md
Instructions for Seven128/project-tiny-context-harness, covering project agent overlay, 本仓库 authoring 例外, minimal context harness protocol, shared engineering quality obligation and default workflow contract.
structured-context-spec CLAUDE.md
Instructions for tim-mccrimmon/structured-context-spec, covering claude.md, structured context specification (scs) — project context, what this project is, repository structure and tools & development commands.