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/clearcotelabs/clearcote-browser/agents-mdgit clone --depth 1 https://github.com/clearcotelabs/clearcote-browserWrote 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/clearcotelabs/clearcote-browser/agents-md)<a href="https://agentmods.dev/instructions/clearcotelabs/clearcote-browser/agents-md"><img src="https://agentmods.dev/badge/instructions/clearcotelabs/clearcote-browser/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 | $0.00843 | $0.00843 |
| Opus 5 | $0.00421 | $0.00421 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
clearcote-browser 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — guide for contributors (human and automated)
This repository is structured so that both people and automated coding tools can navigate, build, and contribute to it without guesswork. If you're an automated contributor, read this first.
What this project is
Clearcote Browser: an open-source, reproducible Chromium build with engine-level privacy/identity controls. Base is ungoogled-chromium; changes are delivered as readable source patches. Target platform is Windows x64 first; the build can be produced on Linux (native or cross-compile).
Repository layout
clearcote-browser/
├── README.md # what/why, quickstart, credits
├── ROADMAP.md # phased plan
├── AGENTS.md # this file
├── CONTRIBUTING.md # contribution workflow
├── CREDITS.md # upstream attributions + licenses
├── DISCLAIMER.md # responsible use + legal
├── UPSTREAM_REVISION # pinned Chromium revision the patches target
├── build.sh # one-shot Linux cross-build orchestrator
├── scripts/ # numbered build stages (fetch, toolchain, windows-sdk, build, package)
├── patches/ # Clearcote's source patches (unified diffs) + series
├── config/ # args.gn and build configuration
└── docs/
├── BUILDING.md # build from source
├── VERIFY.md # verify a release
├── RELEASING.md # maintainer release runbook (canonical)
├── PATCHES.md # patch-set overview
├── RESEARCH.md # design research
└── RESEARCH-DOSSIER.md # deep build/stealth dossier
Conventions
- Patches over forks. Changes to Chromium are unified diffs under
patches/, listed inpatches/series, applied with the ungoogledpatches.pytooling. Keep one logical change per patch with a descriptive name and a header comment explaining why. - Pin everything. Patches target the revision in
UPSTREAM_REVISION. If you bump it, re-test the whole series and update both together. - Engine-level, not JS injection. Identity/privacy behavior belongs in compiled code, not in injected scripts.
- No secrets, no blobs. Never commit credentials, tokens, or opaque binaries. The tree is source + text patches only.
- Privacy-relevant patches are mandatory. Do not drop a privacy/identity patch to make a build pass; fix the patch.
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.
- 4d ago First seen · 71 lines · 843 tokens per session scan A 291f67b7605f
clearcote-browser AGENTS.md is an instructions file published in the GitHub repository clearcotelabs/clearcote-browser (126 stars, last pushed 19d ago), licensed BSD-3-Clause. It adds 843 tokens to every session, about $0.0042 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
fortress AGENTS.md
AGENTS.md instructions for tiliondev/fortress, covering fortress — agent setup guide, ... drive it (section 2) .., 3. persona (optional) — override any fingerprint surface, rules an agent must follow and verify authenticity.
browserpane AGENTS.md
AGENTS.md instructions for ITmedes/browserpane, covering browserpane agent guide, what browserpane is, current support matrix, architecture map and protocol and media facts.
browserpane CLAUDE.md
Claude Code instructions for ITmedes/browserpane: This repo keeps its canonical project instructions in AGENTS.md.
refract AGENTS.md
AGENTS.md instructions for valternunez/refract, covering refract — agent playbooks, playbook: verify a responsive bug fix, playbook: visual-diff before merge, playbook: screenshot a page behind a login and playbook: find horizontal overflow on a pr preview.
playwriter AGENTS.md
Instructions for remorses/playwriter, covering backward compatibility, architecture, development, running mcp locally and running cli locally.
dev-browser AGENTS.md
AGENTS.md instructions for SawyerHood/dev-browser, covering claude.md, tooling and validation.