Borrowing it
Nothing to install: this file belongs to Nitjsefnie-Harness-Commons/daedalus. 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/Nitjsefnie-Harness-Commons/daedalus/main/AGENTS.mdgit clone --depth 1 https://github.com/Nitjsefnie-Harness-Commons/daedalusWrote 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/nitjsefnie-harness-commons/daedalus/agents-md)<a href="https://agentmods.dev/instructions/nitjsefnie-harness-commons/daedalus/agents-md"><img src="https://agentmods.dev/badge/instructions/nitjsefnie-harness-commons/daedalus/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 5.1 | $0.06053 | $0.06053 |
| Opus 5 | $0.03027 | $0.03027 |
| Sonnet 5 | $0.01211 | $0.01211 |
| Haiku 4.5 | $0.00605 | $0.00605 |
Grade A, and why
daedalus 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 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daedalus
Daedalus is a Chrome-extension-based remote control system for matching web pages — eval bridge, screenshots, CDP, cookies, network capture, hotfixes, declarativeNetRequest blocking.
Read README.md first — it is the reference for the command surface, install, and usage.
<investigate_before_answering>
Never claim anything about this codebase's API, field names, or endpoints without opening the file. Field names (id, code, type, tab, token) are exact — verify against server.py or this file before writing bridge commands.
</investigate_before_answering>
Extension (extension/)
- Token: auto-generated on first install, stored in
chrome.storage.local. content.js(ISOLATED world): message relay between page and background. On load it asks the background to replay hotfixes (replayHotfixes); the background picks the eligible fixes from the extension-widedaedalus-hotfixesrecord and runs each through the eval routing below, so a page whose CSP forbids dynamic compilation is reached over CDP. Hotfix source is page-observable by design — it executes in the page — but is no longer posted into it.page.js(MAIN world): the last-resort page relay'snew Function/evaland Blob-script paths, reached only after the background's source-free probe and CDP fallback cannot run submitted source. A hostile same-tab page can choose the relay's one-shot JavaScript value. Exposes the documentedwindow.GMTampermonkey-style subset (xmlhttpRequest,openInTab, storage methods,addStyle, etc.); cookie operations remain typed operator commands, with no page-facingGM.cookiesurface.background.js(service worker): SSE stream, command dispatch, fetch relay, screenshots, CDP, cookies, tabs, downloads, notifications.- Eval routing: a constant MAIN-world
Functionprobe carrying no submitted source runs first.trueselects banner-freepage-maininjection; any other result selects the CDP CSP fallback, whose successful attachment shows Chrome's debugger banner. Once either channel dispatches submitted source, every outcome is terminal; only attach or shape failure before source runs reaches the page relay. - CDP
Runtime.evaluateuses REPL mode, reads direct values by reference, bounds promise settlement at 10 seconds, and releases result and exception handles even when a kept session or capture holds the attachment. - Trust: a page you do not control can choose the returned value on any channel. On
page-mainits ownevalandFunctionbindings can also read the submitted source; oncdpit can choose the value whenever that source uses page-controlled state or page promise machinery. Theworldfield (page-main,cdp,page:<hostname>) records the channel, not whether to trust the value; the background adds the mandatorypage:prefix, so relay hostnames cannot collide with the other two — a descriptive property, not a trust boundary. - The relay admits 1,000 live entries; a new one at capacity gets a terminal error without eviction, and a live entry expires with one terminal error after 300,000 ms.
- Eval routing: a constant MAIN-world
- Tab tracking:
chrome.tabsAPI, registered on create/update with a 30schrome.alarmsheartbeat.
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 Changed · +15 lines · +1,048 tokens per session eaa223a221ec
- 7d ago First seen · 110 lines · 5,005 tokens per session scan A 2c3cf6ff0f55
daedalus AGENTS.md is an instructions file published in the GitHub repository Nitjsefnie-Harness-Commons/daedalus (1 stars, last pushed 2d ago), licensed MIT. It adds 6,053 tokens to every session, about $0.0303 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.