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/ericc-ch/copilot-api/agents-mdgit clone --depth 1 https://github.com/ericc-ch/copilot-apiWhat 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 | $0.00441 | $0.00441 |
| Opus 5 | $0.00220 | $0.00220 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
copilot-api 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- copilot-proxy-api AGENTS.md — 100% identical, 0 lines differ
What it actually says
AGENTS.md
Build, Lint, and Test Commands
- Build:
bun run build(uses tsup) - Dev:
bun run dev - Lint:
bun run lint(uses @echristian/eslint-config) - Lint & Fix staged files:
bunx lint-staged - Test all:
bun test - Test single file:
bun test tests/claude-request.test.ts - Start (prod):
bun run start
Code Style Guidelines
- Imports:
Use ESNext syntax. Prefer absolute imports via~/*forsrc/*(seetsconfig.json). - Formatting:
Follows Prettier (withprettier-plugin-packagejson). Runbun run lintto auto-fix. - Types:
Strict TypeScript (strict: true). Avoidany; use explicit types and interfaces. - Naming:
UsecamelCasefor variables/functions,PascalCasefor types/classes. - Error Handling:
Use explicit error classes (seesrc/lib/error.ts). Avoid silent failures. - Unused:
Unused imports/variables are errors (noUnusedLocals,noUnusedParameters). - Switches:
No fallthrough in switch statements. - Modules:
Use ESNext modules, no CommonJS. - Testing:
Use Bun's built-in test runner. Place tests intests/, name as*.test.ts. - Linting:
Uses@echristian/eslint-config(see npm for details). Includes stylistic, unused imports, regex, and package.json rules. - Paths:
Use path aliases (~/*) for imports fromsrc/.
This file is tailored for agentic coding agents. For more details, see the configs in eslint.config.js and tsconfig.json. No Cursor or Copilot rules detected.
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.
- yesterday First seen · 48 lines · 441 tokens per session scan A 690864503b95
copilot-api AGENTS.md is an instructions file published in the GitHub repository ericc-ch/copilot-api (4,103 stars, last pushed 9mo ago), licensed MIT. It adds 441 tokens to every session, about $0.0022 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 2026-08-30.
Other instructions, from other repositories
ida-pro-mcp CLAUDE.md
Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.
spec-kitty AGENTS.md
Instructions for Priivacy-ai/spec-kitty, covering spec kitty development guidelines, ⚠️ critical: load the project charter first, ⚠️ critical: template source location, ⚠️ critical: use canonical sources, never improvise and ⚠️ critical: git workflow — no direct pushes to origin/main.
apm python.instructions.md
Python development guidelines.
sm64ds-decomp AGENTS.md
Instructions for tangosdev/sm64ds-decomp, covering posting a pr (for ai agents and their humans), the one rule that matters, what goes where, which directory under src/ and shared headers (include/).
NeuroAPI AGENTS.md
Instructions for neurogen-dev/NeuroAPI, a project described as: NeuroAPI: российский AI API для Codex CLI и Claude Code — безопасные one-click установщики для Windows и macOS.
copilot-proxy-api CLAUDE.md
Instructions for voidsteed/copilot-proxy-api, covering claude.md, project overview, common commands, architecture and entry points & cli structure.