Reviewer round 4 (9/6/9/9/7/9) caught that round 3 only fixed the
Quick start: the bare-login default survived in the four highest-
traffic surfaces. All inverted to self-host-first:
- README HERO code block (+ the other-machine one-liner and the
every-other-device shorthand): bdrive login https://your-hub, with
Cloud as a clearly-labeled waitlist callout
- plugin/commands/install.md + init.md step 2: ask for the team's hub
URL; bare 'bdrive login' explicitly flagged as targeting the
not-yet-open Cloud
- SKILL.md walkthrough step 1 + the hub-example comment
- website hero terminal animation: 'syncing → your team's hub', share
URL on a neutral acme-hub.example host (og:url and the coming-soon
card untouched — those are honest)
- README's login reference sentence now says the beardrive.ai default
is waitlist-only
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
New command printing a file's hub viewer URL: sign-in + project-org
membership required to open (the internal counterpart to bdrive share's
public links). Computed locally from the mount config — hub origin +
project id from the remote, path segments percent-encoded with literal
slashes; unsynced paths (ignored, or outside a --shared scope) are
refused so nobody gets handed a 404. --sync pushes first so a
just-created file's link resolves immediately; no arg = project home.
The plugin docs now instruct agents to include this link in their reply
whenever they create a shareable artifact (.md/.html/.csv/...) in the
shared folder, reserving bdrive share for people outside the hub:
SKILL.md command map + 'Share what you make' guidance, install.md root
pointer template + payoff step, README, CLAUDE.md.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
Field report: an agent session read a dozen-plus files via Bash
(grep/cat/tail/find) and Grep, but read heat showed almost nothing —
the read-log hook only matched the native Read tool.
- matchers broadened per platform: claude Read|Grep|Bash, codex
read_file|shell, gemini +search_file_content|run_shell_command,
hermes read_file|grep|bash; plugin hooks.json matches Read|Grep|Bash
- read-log is now tool-aware: shell events mine the command line for
existing files it names (redirect targets and flags excluded), grep
events mine the response for the files the matches came from
(content lines and filename lists), and listing tools (Glob, ls) are
deliberately ignored — seeing a file's name is not reading it
- hooks install upgrades a registered hook's stale matcher in place, so
re-running it after a binary upgrade rolls coverage out to existing
projects instead of being skipped by the idempotency marker
- docs: SKILL.md platform table + read-heat wording, install/init
commands, README command table
Note from the same report, verified not a bug: read-log resolves the
mount via the folder's own .bdrive/config.json (config.ResolveMount),
so a stale duplicate registry entry cannot swallow reads.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
Replace the old "append conventions to CLAUDE.md" step with a two-file
pattern for teaching agents a newly mounted shared folder:
- <shared>/AGENTS.md (synced): the team's single source of truth for the
folder's structure and conventions — scaffolded once by the project
creator, read (never rewritten) by joiners.
- A repo-root AGENTS.md/CLAUDE.md pointer (per machine, not synced): the
awareness/routing layer. Required because discovery differs by
platform — Claude Code and Hermes load nested instruction files lazily
(only after entering the folder), and Codex never discovers them at
all (root→cwd path only).
SKILL.md gains a "Teaching agents the folder" section with the platform
discovery table and a first-contact orientation ritual; /beardrive:install
step 4 and /beardrive:init step 6 now offer both files as separate
consents; install.md step 3 gains the same never-sync-a-repo-root hard
rule init.md already had; README/CLAUDE.md descriptions updated.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
Pre-existing working-tree edits landed with this batch: SKILL.md and
/beardrive:init gain guidance for gbrain-backed shared folders — elect a
single enrichment owner (everyone else indexes read-only), route member
captures into per-member subtrees, treat conflict copies as the canary
for a second enricher, and follow the owner's pull→import→enrich→write
cycle discipline to avoid silently reverting human edits.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
Admin/org-owner Insights view (⋯ menu): dependency-free SVG scatter of
every file by 30-day reads × days since last change, log scales, with the
hot-but-stale danger quadrant shaded and a ranked fix-these-first list;
lens toggle for all/human/agent reads. The Claude Code plugin gains a
PostToolUse(Read) hook so plugin users feed agent-read telemetry without
project-level hook registration. Docs synced: README, SKILL.md,
plugin install/init commands, CLAUDE.md, design doc marked implemented.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
`bdrive hooks install` detects the agent platforms in use — Claude Code
(.claude/), Codex (.codex/), Gemini CLI (.gemini/), Hermes (~/.hermes/) —
and idempotently merges beardrive's turn-boundary sync hooks into each
platform's own hook config (JSON for claude/codex/gemini, YAML for
hermes), preserving existing hooks. All four pipe hook JSON with a
session_id, so one POSIX-sh hook command serves every platform: pull at
turn start, push after edits, changes stamped "<agent> session <id>".
Bare `bdrive hooks` prints the detection/registration table.
The beardrive skill now runs it automatically after `bdrive init`, and
/beardrive:install's hand-maintained settings.json block is replaced by
the command, so the hook content has one source of truth in the binary.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
A subdirectory with its own .bdrive/config.json now syncs only through
its own project: the parent mount never scans into it, materializes
over it, or emits deletes for paths under it (cached paths are dropped
without delete ops, the same posture as newly ignored files). Detection
is presence-based (config.IsMount) so even a corrupt nested config
still fences. This makes the team-knowledge-folder-inside-a-personal-
mount topology safe.
The plugin's init command and skill gain a "connecting knowledge
tooling" playbook: a detection ladder (gbrain -> OKF wiki -> plain
docs folder -> starting-point menu) and two hard rules — one transport
per folder (git-tracked dirs are handed off via git rm --cached +
gitignore before syncing) and knowledge-as-scoped-subfolder (never a
repo root). Conflict copies documented with their exact glob
(*.bdrive-conflict-*), since openknowledge validate cannot see them.
New flow tests: shared-subfolder scope both ways, teammate connect
over identical/divergent local content, nested mount syncing
independently on two projects, and a guard pinning the conflict-copy
filename to the documented glob.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01P5cxPQdSGJnjXCYY9GeWXt
bdrive mnt was replaced by bdrive init, but the plugin still taught the
old model — /beardrive:mount even instructed Claude to run a command
that no longer exists.
- /beardrive:mount -> /beardrive:init: login-aware, uses bdrive init
(resume/create/connect, --shared), points at /beardrive:install for
the full team setup.
- Skill description reframed around "start syncing a project"; "mount a
folder" kept as a trigger phrase since people still say it.
- status command, marketplace manifest, README plugin section, and
CLAUDE.md updated to match.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Share links (bdrive share <file>, or the web UI's Share button):
- Mint an unguessable public URL (/s/<token>) anyone can open — no
account. HTML renders as a page, markdown gets a standalone shell,
PDFs open inline; ?download=1 attaches.
- Sandboxed: /s/* responses carry CSP `sandbox allow-scripts` + nosniff
and never see auth cookies, so shared content's scripts run in an
opaque origin and can't touch hub sessions.
- Links serve the file's LATEST synced content and live until revoked;
--expires makes self-destructing ones; --list/--revoke manage them.
Re-sharing a file returns the same link. File-backed shares.json.
- CLI resolves the project by walking up to .bdrive/ from the shared
file, warns when the hub address is private (LAN-only links), and
hints when the file hasn't synced yet.
/beardrive:install (plugin command) — team onboarding driven by Claude:
- Ensures the bdrive binary, signs in (bdrive login), runs bdrive init
(whole folder or a shared subfolder like wiki/).
- Asks before appending a CLAUDE.md section that teaches agents to put
shareable artifacts in the shared folder and mint URLs with bdrive
share; asks before registering project-level hooks in
.claude/settings.json: blocking pull at UserPromptSubmit, async push
on PostToolUse Write|Edit — teammates sync with or without the plugin.
- Fix: the plugin hook script still checked for the old `.bdrive` file
and was a silent no-op since the directory change; now checks -d.
Tests: share creation gating, public access + sandbox headers, dedupe,
latest-content semantics, revoke, expiry, markdown/download variants,
list filtering, registry persistence. Docs updated (README sharing +
Claude Code sections, SKILL.md, CLAUDE.md).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
The web server (bdrive web) becomes a full sync hub, and client devices
get one-command onboarding — without ever seeing storage info or holding
cloud credentials:
- bdrive web -c config.json: server configurable from a JSON file
(remote/addr/upload/upload_ttl/projects_db); explicit flags win.
- Hub mode: pointing bdrive web at a storage root hosts many projects,
each under <root>/<project-id>/ (remote.Prefixed). Projects live in a
file-backed registry (projects.json — loaded at open, rewritten
atomically per change) with create-or-join-by-name semantics.
- Per-project APIs: /api/projects (list/create/get) and
/api/p/<id>/{tree,file,render,download,upload/*,store/*}. The web UI
grows a project list with per-project browsing and hash deep links.
- Browser uploads and a store proxy for syncing devices: presigned
direct-to-storage PUTs when the backend can sign (S3 presign, GCS V4
signed URLs; expiring, credential-free), relayed through the server
otherwise. Journals are never presigned — only immutable blobs.
Blobs-before-journal and one-writer-per-journal invariants hold.
- https:// remote backend: a device syncs one hub project through
/api/p/<id>/store/* — mnt/sync/daemon/log all work unchanged.
- bdrive login <url>: verify a hub and remember it as the device default
(settings.json). bdrive init: create-or-join a project named after the
folder (--name/--project override), write .bdrive, seed a starter
.bdriveignore, mount, and start the daemon — one command per project.
- Hard-break rename: .beardrive->.bdrive, .beardriveignore->.bdriveignore,
~/.beardrive->~/.bdrive, BEARDRIVE_HOME->BDRIVE_HOME, temp/conflict
prefixes; old names are no longer read.
- Tests: presigning, project registry persistence, store API validation
and gating, project isolation over live HTTP, browser upload flows, and
two-device convergence through a hub (incl. read-only pull-only mode).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01R7Q9ZKSZRTdvrSJkYLUmYs
Product and project are BearDrive; the CLI binary is bdrive (bdrive mnt,
bdrive sync, ...), the web viewer is bdrive-web. All conventions follow
the full name: .beardrive settings file, .beardriveignore, ~/.beardrive
home, BEARDRIVE_HOME, .beardrive-conflict-* / .beardrive-tmp-* files.
Plugin/skill/marketplace renamed to beardrive (/beardrive:mount).
Module path is now github.com/runbear-io/beardrive — merge only after
renaming the GitHub repo, or go install breaks.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HHEUaYfFHhmDvqLYw74Ehz
- sfs-web (cmd/sfs-web, internal/webapp): read-only Obsidian-style web UI
serving a local folder (default) or an sfs remote; markdown rendering
with [[wikilinks]], task lists and tables, file downloads with ETags,
per-file provenance from the journals; added to goreleaser builds
- .sfs project file (internal/config): per-folder volume/remote/include
settings that travel with the folder, win over the global registry, and
never sync; daemon picks up edits live
- .sfsignore + include lists (internal/syncer): gitignore-style selective
sync with ! re-includes, applied symmetrically in scan and materialize;
newly ignored files stop syncing without being deleted anywhere
- Claude Code plugin (plugin/, .claude-plugin/): sfs skill, /sfs:mount and
/sfs:status commands, turn-boundary sync hooks (blocking pull on prompt,
async push on stop); installable via the repo's marketplace manifest
- CLAUDE.md and .claude project settings for Claude Code development
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HHEUaYfFHhmDvqLYw74Ehz
