Borrowing it
Nothing to install: this file belongs to AnEntrypoint/freddie. 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/AnEntrypoint/freddie/main/AGENTS.mdgit clone --depth 1 https://github.com/AnEntrypoint/freddieWrote 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/anentrypoint/freddie/agents-md)<a href="https://agentmods.dev/instructions/anentrypoint/freddie/agents-md"><img src="https://agentmods.dev/badge/instructions/anentrypoint/freddie/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/anentrypoint/freddie/agents-md"><img src="https://agentmods.dev/badge/instructions/anentrypoint/freddie/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 | $0.02386 | $0.02386 |
| Opus 5.5 | $0.00954 | $0.00954 |
| Sonnet 5.5 | $0.00477 | $0.00477 |
| Haiku 4.5 | $0.00239 | $0.00239 |
Grade A, and why
freddie 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 12d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Freddie is a plugin-based agent harness on the Cordis framework layer (framework/): everything is a plugin. Read docs/architecture.md before changing packages/; documentation rules: docs/AGENTS.md.
Pre-release stance: foundation over blast radius
Remove this section at the first tagged release. Prefer the correct foundation over compatibility shims; rename or repackage freely and update every reference together. Backends reject old on-disk formats: SQLite uses monotonic SCHEMA_VERSION; freddie-session keeps SESSION_FORMAT_VERSION at 0, with no compatibility promise.
Repository layout
framework/ is the first-party Cordis layer (divergence log). packages/<group>/<pkg>/ holds @freddie/freddie-* workspaces (package map). native/ (landlock addon), examples/ (runnable leaves), .agents/ (Agent Notes), docs/ (catalogs), scripts/ (gates).
Commands
pnpm install (node ^22.19 || >=24); pnpm run publint (publish shape); pnpm freddie --profile headless "task", pnpm run demo:cordis and demo:acp need DEEPSEEK_API_KEY. Buildless: packages ship src/**/*.js with no build, clean or typecheck step (development.md).
Host sandbox failures
- With approvals disabled or unrestricted filesystem access, run required commands without a sandbox-permission field; any resulting failure is ordinary command evidence.
- In a confined host, when
gh,pnpmor generator commands fail on sandbox-blocked credentials, network, IPC, file watching or nestedsandbox-exec, retry unchanged with the narrowest host escalation before diagnosing authentication or project failure. - Require sandbox evidence; never bypass a genuine failure or the product sandbox under test.
Verify before pushing
- No automated suite (why): verify by exhaustive manual execution against the real running system, in the same turn and PR. Run the real code path against real state, read the real output, and re-derive the check from the request's own words. A diff's claim about itself is not evidence.
- Match evidence to the surface: live boot (
pnpm freddieor the relevant app entry point) for behavior;pnpm run publintfor package-shape or publish-surface drift. - Run what the change touches; never every check for every change.
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.
- 12d ago Changed · +4 lines · -169 tokens per session 81b786b62829
- 21d ago Changed · +38 tokens per session 8c81d9821011
- 25d ago Changed · +8 lines · +393 tokens per session 93e9a0c42035
- 1mo ago Changed · -61 lines · -1,077 tokens per session 3d6631858373
- 1mo ago Changed · +3 lines · +153 tokens per session 9ee5463a37d1
- 1mo ago Changed · -391 lines · -16,705 tokens per session scan D → A 9d7ef7648329
- 1mo ago First seen · 526 lines · 19,753 tokens per session scan D c9a276c8ceff
freddie AGENTS.md is an instructions file published in the GitHub repository AnEntrypoint/freddie (1 stars, last pushed 5d ago), licensed MIT. It adds 2,386 tokens to every session, about $0.0095 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.