the signals and their derived score are provisional and subject to change.
validate manually before sharing.
e5995d7a3b29228140af779c2ca4b2b47f98ad0b259683fde1f507bf59653cce80348011bc4a96a6Authored: 1 week ago (Wed, 9 Sep 2026 14:22:53 +0000)Match: Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>130f0d6df01d1c63f5254bdf0c1698b331d31285Authored: 1 week ago (Tue, 8 Sep 2026 12:46:02 +0000)Match: Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>80ac86c58d933f167da8791b6da71c8fa2c489f6Authored: 2 weeks ago (Thu, 27 Aug 2026 23:27:04 +0000)Match: Co-authored-by: Cursor <cursoragent@cursor.com>99a949160c4538da6f1af0a7924d0ba3d1879f5eAuthored: 3 weeks ago (Thu, 20 Aug 2026 23:56:22 +0000)Match: Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>c1e07a17d7bc85a1e80463498c7a3b5b82806f92Authored: 1 month ago (Thu, 13 Aug 2026 07:25:31 +0000)Match: Co-authored-by: Claude Fable 5 <noreply@anthropic.com>3d2e2a7ad79302ad8bd34fc00d5ac7360a3d6e83Authored: 1 month ago (Fri, 31 Jul 2026 19:58:07 +0000)Match: Co-authored-by: Cursor <cursoragent@cursor.com>1be1cee5f13328b1f2473fca9b65d38071709c03Authored: 1 month ago (Fri, 31 Jul 2026 18:30:33 +0000)Match: Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>469de8bf4950bc39222e33eccb74581db7a03126Authored: 1 month ago (Thu, 30 Jul 2026 11:59:04 +0000)Match: Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>f06f552ec8a6eba84b847e93e5e93d7722fd4417Authored: 1 month ago (Thu, 23 Jul 2026 17:35:04 +0000)Match: Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>bf27250afeb9aa8dd727f485ed376b560c63b31dAuthored: 1 month ago (Tue, 21 Jul 2026 01:33:23 +0000)Match: Co-authored-by: Cursor <cursoragent@cursor.com>127382ec5a61cdd3f53588e882eb2f5341c59be7Authored: 2 months ago (Tue, 14 Jul 2026 17:35:59 +0000)Match: Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>1c29faf2a605eadc9682224a121d530aed40179fAuthored: 2 months ago (Mon, 6 Jul 2026 13:06:32 +0000)Match: Co-authored-by: Cursor <cursoragent@cursor.com>75c7aaec57ae2aca4344273bb15b7226be73f001Authored: 2 months ago (Mon, 29 Jun 2026 10:46:50 +0000)Match: Co-authored-by: Cursor <cursoragent@cursor.com>d41b01292f52e8130d739b620bbe5012df3192ddAuthored: 2 months ago (Tue, 23 Jun 2026 15:10:48 +0000)Match: Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>fbbcd68b82d7448e1dc825fe59f715a2214ac043Authored: 2 months ago (Mon, 22 Jun 2026 19:44:00 +0000)Match: Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>e33a8cd2620590799911338219195118ba27e4ccAuthored: 3 months ago (Mon, 15 Jun 2026 16:08:31 +0000)Match: Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>797314a6f083a63197e632a267897410230e60a1Authored: 3 months ago (Thu, 11 Jun 2026 18:41:46 +0000)Match: Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>126ad0ae42f2b17a2c6243810e5f13e17efae9c5Authored: 3 months ago (Mon, 8 Jun 2026 15:20:16 +0000)Match: Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>6bb1b650b3a429f69cadb9c73d07a679ea20bd76Authored: 3 months ago (Fri, 5 Jun 2026 08:20:22 +0000)Match: Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>a1d24eda447ac86069eddf3aa1db85cb78f79958Authored: 4 months ago (Thu, 14 May 2026 08:45:28 +0000)Match: Co-authored-by: Cursor <cursoragent@cursor.com>e0f6e9015b6582e3b3f6125f667deecc80e89d4bAuthored: 4 months ago (Mon, 11 May 2026 13:51:10 +0000)Match: Co-authored-by: Cursor <cursoragent@cursor.com>f7462bebf9d062bf12fc2bbe4359054a5208309cAuthored: 4 months ago (Mon, 4 May 2026 18:57:33 +0000)Match: Co-authored-by: Cursor <cursoragent@cursor.com>f3465bb4fd6c53c10881411f8ab639400e750f86Authored: 4 months ago (Fri, 1 May 2026 22:43:20 +0000)Match: Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>761794b174298d1c53de5afbddacb58d90168b47Authored: 4 months ago (Fri, 1 May 2026 18:40:43 +0000)Match: Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com>99c62155d2c356f4cfaeb55c290353ff78ff8fe2Authored: 4 months ago (Fri, 1 May 2026 00:56:59 +0000)Match: Made-with: Cursorc5dbd495702b09934fcde1f652c8772b559bfecfAuthored: 5 months ago (Tue, 14 Apr 2026 14:42:48 +0000)Match: Made-with: Cursorf0ce16404b3771bbbbbe399bf07b9e0ebbace9f8Authored: 5 months ago (Tue, 7 Apr 2026 13:26:33 +0000)Match: Made-with: Cursor55bc3c7913751174c2f727d4d5c16360c85196b5Authored: 5 months ago (Sat, 4 Apr 2026 13:07:56 +0000)Match: Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>a7bade6bac37ccfc9dc2550017498be345e254dfAuthored: 5 months ago (Wed, 25 Mar 2026 13:02:07 +0000)Match: Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>1f1b6b01cb490207d029e33a12ceb244d607b292Authored: 5 months ago (Fri, 20 Mar 2026 18:20:59 +0000)Match: Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>0266eb315c2cdc7d9d3710b4c807ce2c70076af4Authored: 6 months ago (Thu, 12 Mar 2026 03:16:03 +0000)Match: Made-with: Cursor2ac2e381791a131f603bc395b240cc9e8ac293d5Authored: 6 months ago (Fri, 6 Mar 2026 15:32:28 +0000)Match: Made-with: Cursora13d9c0b7ae1df5f326f1ad0d4fe4c60218f36abAuthored: 6 months ago (Thu, 5 Mar 2026 10:45:09 +0000)Match: Made-with: Cursor01f6d7a8716a61ded4406f398707d7e1f01cf256Authored: 6 months ago (Wed, 4 Mar 2026 13:14:19 +0000)Match: Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>5d80fd8a181c0f21a74c98fb055929b118fa5008Authored: 6 months ago (Mon, 2 Mar 2026 18:12:55 +0000)Match: Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>agents/skills/create-contributor-prs/SKILL.mdTool: unspecified---
name: create-contributor-prs
description:
For an external contributor's open PRs to brave/brave-core, ensure the
`sync-and-rebase-pr-from-fork.yml` workflow has been dispatched for each PR's
latest commit SHA — so a `contributor-*` draft PR exists inside
brave/brave-core and CI can run. Invoke when the user says something like
"create contributor PRs for <user>", "sync contributor PRs <list>", "run the
rebase-from-fork workflow for these PRs", or passes a GitHub username / list
of PR URLagents/skills/preflight/SKILL.mdTool: unspecified---
name: preflight
description:
'Run all preflight checks (format, gn_check, presubmit, build, tests) to make
sure the current work is ready for review.'
---
# Preflight Checks
Run all preflight checks to make sure the current work is ready for review.
Execute each step sequentially and stop immediately if any step fails.
## Arguments
- **`all`** — Run all test suites (brave_browser_tests, brave_unit_tests,
brave_component_unittests) without filters, instead of only running tests
affected by agents/skills/force-push-downstream/SKILL.mdTool: unspecified---
name: force-push-downstream
description:
'Force-push a branch and all its downstream branches to origin. Auto-detects
the downstream tree and skips branches already up-to-date. Triggers on: force
push downstream, push chain, push all branches.'
argument-hint: '[starting-branch]'
disable-model-invocation: true
---
# Force Push Downstream
Force-push a branch and all its downstream branches to their respective remotes.
Skips branches whose local and remote tips already match.
## Arguments
- **`stagents/skills/plaster-from-patch/SKILL.mdTool: unspecified---
name: plaster-from-patch
description:
"Create a Plaster (`rewrite/*.yaml`) config for an existing Brave-core
Chromium `.patch`, authoring an intent-conveying regex match per the Plaster
Dos and Don'ts, then verifying it by running `plaster.py apply` and diffing
the regenerated patch against the original. Does not modify sources or create
other files. Triggers on: plaster from patch, convert patch to plaster,
plasterize, make a plaster."
argument-hint:
'<patch file, source path, or nothing agents/skills/check-upstream-flake/SKILL.mdTool: unspecified---
name: check-upstream-flake
description:
"Check if a failing test is a known upstream flake in Chromium's LUCI Analysis
database. Provides flakiness statistics, verdict, and recommendation for
filter file decisions. Triggers on: check upstream flake, is this test flaky
upstream, check luci flakiness, upstream flake check."
argument-hint: <TestSuite.TestMethod>
disable-model-invocation: true
---
# Check Upstream Flake
Check if a failing test is a known upstream flake in the Chromium LUCI Analysiagents/skills/top-crashers/SKILL.mdTool: unspecified---
name: top-crashers
description:
"Get top crashers from Brave's Backtrace crash reporting. Shows crash
signatures, stacks, platforms, versions, channel breakdown, code origin, and
regression detection. Triggers on: top crashers, crash report, what's
crashing, top crashes, crash analysis, regression crashers, new crashes."
disable-model-invocation: true
argument-hint:
'[--days 7] [--platform Windows] [--compare 2] [--new-only] [--crashes-only]
[--channels nightly,beta] [--brave-only]'
---
# Tagents/skills/uplift/SKILL.mdTool: unspecified---
name: uplift
description: "Create an uplift PR that cherry-picks merged PRs from a contributor into a target branch (beta or release). Defaults to broad eligibility; the scope can be narrowed via a free-form description (e.g. 'only automated test and crash fixes'). Triggers on: /uplift, create uplift, uplift PRs."
argument-hint: [github-username] [beta|release] [all|<num>d|PR1,PR2,PR3] [<scope description in English>]
disable-model-invocation: true
allowed-tools: Bash, Read, WebFetch, Grep, Glob
---
# agents/skills/review/SKILL.mdTool: unspecified---
name: review
description:
'Review code for quality, root cause analysis, and fix confidence. Supports PR
review and local review of uncommitted/branch changes. Default mode is local
(reviews current branch changes). Triggers on: review pr, review this pr,
/review <pr_url>, /review local, /review, check bot pr quality.'
disable-model-invocation: true
allowed-tools:
Bash(gh issue list:*), Bash(gh issue view:*), Bash(gh pr list:*), Bash(gh pr
view:*), Bash(gh pr diff:*), Bash(git diff:*), Bash(agents/skills/pr/SKILL.mdTool: unspecified---
name: pr
description: Create a pull request for the current branch using `gh`.
disable-model-invocation: true
---
# Create Pull Request
Create a pull request for the current branch using `gh`.
## Current State
- Branch: !`git branch --show-current`
- Commits on branch: !`git log master..HEAD --oneline`
- Changed files: !`git diff master...HEAD --stat`
## Steps
### 1. Gather context
- Review the commits and changed files above.
- Check if the branch is associated with a GitHub issue (look at brancagents/skills/check-milestones/skill.mdTool: unspecified---
name: check-milestones
description: "Check and fix milestones on PRs and their associated issues. Sets PR milestones based on the branch they merged into, and issue milestones based on the smallest version with a merged uplift. Triggers on: check milestones, fix milestones, /check-milestones."
argument-hint: [github-username] [all|PR1,PR2,PR3]
disable-model-invocation: true
allowed-tools: Bash, Read, WebFetch, Grep, Glob
---
# Check Milestones
Check and fix milestones on a contributor's merged PRs andagents/skills/add-best-practice/SKILL.mdTool: unspecified---
name: add-best-practice
description:
'Add a new best practice to the appropriate doc. Checks for duplicates,
assigns stable IDs, creates new category docs if needed. Triggers on: add best
practice, new best practice, add bp, new bp.'
argument-hint: '<best practice description>'
disable-model-invocation: true
allowed-tools:
Bash(python3:*), Bash(git:*), Bash(gh:*), Bash(ls:*), Read, Grep, Glob, Edit,
Write, Agent, WebFetch
---
# Add Best Practice
Add a new best practice rule to the correct beagents/skills/rebase-downstream/SKILL.mdTool: unspecified---
name: rebase-downstream
description:
'Rebase a tree of dependent branches (including siblings) after upstream
changes. Auto-detects downstream branches and rebases each in order. Triggers
on: rebase downstream, rebase chain, propagate changes downstream.'
disable-model-invocation: true
---
# Rebase Downstream Tree
Rebase a tree of dependent branches after upstream changes have been made.
Auto-detects the downstream branch tree (including sibling branches), rebases
each branch in order, resolves agents/skills/make-ci-green/SKILL.mdTool: unspecified---
name: make-ci-green
description:
'Re-run failed CI jobs for a brave/brave-core PR. Detects failure stage and
uses WIPE_WORKSPACE for build/infra failures. Triggers on: make ci green,
retry ci, rerun ci, fix ci, re-run failed jobs, retrigger ci.'
argument-hint: '<pr-number> [--dry-run]'
disable-model-invocation: true
---
# Make CI Green
Re-run failed Jenkins CI jobs for a brave/brave-core PR. Automatically detects
the failure stage and decides whether to use WIPE_WORKSPACE (for build/infra
failuragents/skills/fix-bp-docs/SKILL.mdTool: unspecified---
name: fix-bp-docs
description:
'Audit and fix best practices docs for stale references, duplicates, obsolete
content, and formatting issues. Triggers on: fix bp docs, fix best practice
docs, audit bp docs.'
disable-model-invocation: true
allowed-tools:
Bash(find:*), Bash(ls:*), Bash(head:*), Bash(git:*), Bash(python3:*), Read,
Grep, Glob, Edit
---
# Fix Best Practices Docs
Audit all best practices documentation files for issues and fix them. This skill
must be run from the `brave-core` direcagents/skills/prs-reviewed/SKILL.mdTool: unspecified---
name: prs-reviewed
description:
'Get PRs a user reviewed on brave/brave-core. Shows PR number, title, author,
state, and links. Triggers on: prs reviewed, reviewed prs, review activity,
what did I review, review history.'
argument-hint: '<username> <num>d'
disable-model-invocation: true
---
# PRs Reviewed
Query GitHub for pull requests a user has reviewed on `brave/brave-core` within
a given time window.
---
## When to Use
- **Checking review activity** for a team member
- **Weekly/daily stanagents/skills/review-prs/SKILL.mdTool: unspecified---
name: review-prs
description:
'Review PRs in the configured PR repository for best practices violations.
Supports single PR (#12345), state filter (open/closed/all), and auto mode for
cron. Triggers on: review prs, review recent prs, /review-prs, check prs for
best practices.'
argument-hint:
'[days|page<N>|#<PR>] [open|closed|all] [auto] [reviewer-priority]'
disable-model-invocation: true
allowed-tools: Bash(gh pr diff:*)
---
# Review PRs for Best Practices
Scan recent open PRs in the configagents/skills/clean-branches/SKILL.mdTool: unspecified---
name: clean-branches
description:
'Delete local branches whose PRs have been merged upstream. Checks GitHub PR
status for each branch. Triggers on: clean branches, delete merged branches,
prune branches, branch cleanup.'
disable-model-invocation: true
---
# Clean Branches - Delete Merged Local Branches
Clean up local branches by checking their GitHub PR status and deleting those
that have been merged.
## Steps
1. **Fetch and list branches** — Fetch the latest remote state, then get all
loagents/skills/impl-review/SKILL.mdTool: unspecified---
name: impl-review
description:
'Implement review feedback on a PR. Checks out the branch, applies
reviewer-requested changes, runs preflight, commits, and pushes. Triggers on:
impl-review, implement review, implement review feedback, address review
comments.'
argument-hint: '<pr-number>'
disable-model-invocation: true
---
# Implement Review Feedback
Checkout a PR's branch, implement the reviewer's feedback, run preflight checks,
commit, and push.
## Arguments
- **`<pr-number>`** (required) third_party/rust/chromium_crates_io/vendor/corez-v0_1/AGENTS.mdTool: agents-md# corez - Agent Guidelines
> This file is read by AI coding agents (Claude Code, GitHub Copilot, Cursor, Devin, etc.).
> It provides project context and contribution policies.
>
> For the full contribution guide, see [CONTRIBUTING.md](CONTRIBUTING.md).
`corez` is a minimal, safe, `no_std`-compatible crate providing `Read` and
`Write` traits for the Zcash ecosystem. When the `std` feature is enabled (the
default), all types are re-exported directly from `std::io` via conditional
compilation. The `no_std` ptools/crates/vendor/zerocopy/AGENTS.mdTool: agents-md<!-- Copyright 2025 The Fuchsia Authors
Licensed under a BSD-style license <LICENSE-BSD>, Apache License, Version 2.0
<LICENSE-APACHE or https://www.apache.org/licenses/LICENSE-2.0>, or the MIT
license <LICENSE-MIT or https://opensource.org/licenses/MIT>, at your option.
This file may not be copied, modified, or distributed except according to
those terms. -->
# Development Instructions
This repository uses a wrapper script around Cargo to ensure consistent toolchain usage and configuration.
## Build anAGENTS.mdTool: agents-mdRefer to canonical agent instructions in `.claude/CLAUDE.md`.
.claude/CLAUDE.mdTool: claude-codeThis is the Brave Core repository, which contains a set of complex changes and
scripts used for deeply modifying Chromium to make the Brave browser for
windows, mac, linux, android and ios.
All files in this src/brave directory are for Brave customizations. The chromium
repository is the parent directory at src/ and all other children of that
directory.
## Conventions
- Keep comments, commit messages, and PR descriptions succinct — essential "why"
only.
## Development Tasks
When asked to explore a .claudeTool: claude-code.claudeTool: claude-code.claudeTool: claude-code.claudeTool: claude-codetools/crates/vendor/camino/.claudeTool: claude-codenone