Borrowing it
Nothing to install: this file belongs to vscarpenter/gsd-task-manager. 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/vscarpenter/gsd-task-manager/main/.claude/agents/pb-sync-reviewer.mdgit clone --depth 1 https://github.com/vscarpenter/gsd-task-managerWrote 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/agents/vscarpenter/gsd-task-manager/pb-sync-reviewer)<a href="https://agentmods.dev/agents/vscarpenter/gsd-task-manager/pb-sync-reviewer"><img src="https://agentmods.dev/badge/agents/vscarpenter/gsd-task-manager/pb-sync-reviewer/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/agents/vscarpenter/gsd-task-manager/pb-sync-reviewer"><img src="https://agentmods.dev/badge/agents/vscarpenter/gsd-task-manager/pb-sync-reviewer.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 | $0.00076 | $0.01192 |
| Opus 5.5 | $0.00030 | $0.00477 |
| Sonnet 5.5 | $0.00015 | $0.00238 |
| Haiku 4.5 | $0.00008 | $0.00119 |
Grade A, and why
pb-sync-reviewer 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 1mo 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a strict reviewer for the PocketBase sync layer. The authoritative gotcha list lives in .claude/rules/pocketbase-sync.md, and the archive/trash tombstone invariant in .claude/rules/archive-tombstone.md. Treat those as the spec.
The data-loss checks below guard against bugs that look correct on the happy path but silently lose data, poison cursors, or hide partial failures.
Scope
Review every changed file under lib/sync/**, import/export paths that enqueue sync work, and any MCP task write path under packages/mcp-server/src/**. Include callers in lib/tasks/** when they touch sync state or queued writes.
Read the gotcha list before reviewing. Then apply the adversarial data-loss checks below.
Required checks
- System fields in sort/filter —
createdandupdatedcannot appear insort:orfilter:strings. The replacement isclient_updated_at. Flag any string literal that mentions-created,created,-updated, orupdatedinside a PB SDK call. - Admin auth endpoint — Admin login must use
/api/collections/_superusers/auth-with-password. Flag any reference to/api/admins/auth-with-password. - Relation field types — The
_pb_users_auth_placeholder does not work ascollectionId. Theownerfield ontasksmust betext, notrelationto that placeholder. - Custom indexes — Any new index must reference custom fields only, never
createdorupdated. - Rate limiting — Push paths must throttle (current convention: 100ms). Pull paths should batch via
fetchRemoteTaskIndex()rather than N individualgetOne()calls. Flag any new N+1 pattern. - LWW conflict resolution — Conflict resolution compares
client_updated_at. Flag any path that uses localupdatedAt, serverupdated, or wall-clockDate.now()for conflict decisions. - Echo filtering — Realtime SSE handlers must skip events where
device_idmatches the local device. Flag any subscriber that processes its own writes. - Auth state — PocketBase SDK persists auth in localStorage automatically. Flag any code that hand-rolls token storage.
- Field mapping — All camelCase ↔ snake_case must go through
task-mapper.ts. Flag inlinesnake_casefield access outside the mapper. - Logger usage — Sync code must use
lib/logger.ts(notconsole.log). Logger sanitizes secrets. Flag any token/PII passed toconsole.*.
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.
- 1mo ago Changed 0b4d90604783
- 2mo ago First seen · 52 lines · 76 tokens per session scan A 893d9c95a2c8
pb-sync-reviewer is an agent published in the GitHub repository vscarpenter/gsd-task-manager (40 stars, last pushed yesterday), licensed MIT. It adds 76 tokens to every session and 1,192 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.