gsd-task-manager: Skill for Claude Code

.agents/skills/pb-collection/SKILL.md

pb-collection is a skill for Claude Code from vscarpenter/gsd-task-manager. It costs 71 tokens per session (1,537 once invoked), scanned A, original, MIT.

A design-system styling guide for applying Inkwell's existing visual rules to a page or component without changing its content or behavior.

In plain words
What is it for?
Use it to restyle existing pages, HTML explainers, documentation, or Tailwind CSS projects with Inkwell's tokens and reusable styling patterns.
Why use it?
It prevents a page from accumulating competing colors, spacing rules, and CSS conventions.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is vscarpenter/gsd-task-manager's own configuration. It tells Claude Code how to work on gsd-task-manager itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gsd-task-manager configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/vscarpenter/gsd-task-manager/main/.agents/skills/pb-collection/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vscarpenter/gsd-task-manager

Made for: Claude Code.

Wrote 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.

agentmods badge for pb-collection

README.md
[![agentmods](https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/pb-collection.svg)](https://agentmods.dev/skills/vscarpenter/gsd-task-manager/pb-collection)
Your own site
<a href="https://agentmods.dev/skills/vscarpenter/gsd-task-manager/pb-collection"><img src="https://agentmods.dev/badge/skills/vscarpenter/gsd-task-manager/pb-collection.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.01537
Opus 5 $0.00036 $0.00768
Sonnet 5 $0.00014 $0.00307
Haiku 4.5 $0.00007 $0.00154

Measured 6d ago against content hash b0b627f22f07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pb-collection 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 6d 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.

.agents/skills/pb-collection/SKILL.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pb-collection — End-to-end PocketBase tasks-collection field change

This skill walks through every place a field touches when added to the synced tasks collection. Skipping any step has bitten us before — the order matters.

When to invoke

User says any of:

  • "Add a <field> to tasks"
  • "Sync <field> across devices"
  • "PocketBase needs <field>"
  • "Update the tasks schema"

Do NOT invoke for local-only Dexie fields (those don't need the PB layers).

Prerequisites — verify before touching code

  1. Read AGENTS.md → "PocketBase v0.23+ Gotchas" section. The gotchas below are condensed but the source of truth is there.
  2. Confirm the user has the PocketBase admin password handy (needed to run scripts/setup-pocketbase-collections.sh).
  3. Confirm the field is not a system field name (id, created, updated, collectionId, collectionName).
  4. Confirm field type is supported by both Dexie and PocketBase: text, number, bool, json, date. Never use relation to _pb_users_auth_ (placeholder doesn't resolve at runtime).

Step order (do not reorder)

1. Update Zod schema — lib/schema.ts

  • Add the field to the taskSchema (and taskInputSchema if user-settable).
  • Use .safeParse() callers; if this is a user-input path, the schema must already be wired to a safeParse boundary.
  • For optional fields, default to a sensible value (.optional().default(...)) so legacy tasks parse without error.
  • Update both exportSchema (.strict()) and importSchema (.strip()).

2. Update task-mapper — lib/sync/task-mapper.ts

  • Add the camelCase ↔ snake_case mapping. PocketBase uses snake_case; the app uses camelCase.
  • Both directions: mapToRemote() and mapFromRemote().
  • Test the mapper round-trip in tests/data/task-mapper.test.ts.

3. Update PocketBase collection — scripts/setup-pocketbase-collections.sh

  • Add the field to the tasks collection definition in the script.
  • If the field needs to be sortable/filterable, add a custom index — but the index must reference the new field, NEVER created or updated.
  • Run the script against https://api.vinny.io (requires _superusers admin auth — endpoint is /api/collections/_superusers/auth-with-password, not /api/admins/).
  • Verify the field appears in PB admin UI before continuing.

Read the full file on GitHub · 111 lines

Changes

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.

  1. 6d ago First seen · 111 lines · 71 tokens per session scan A b0b627f22f07

Subscribe to this mod's changes

pb-collection is a skill published in the GitHub repository vscarpenter/gsd-task-manager (25 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,537 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

organize-database

Transform unstructured Notion pages into a well-designed database with proper schema and migration.

n24q02m/better-notion-mcp · 21 tokens

lastest

Run visual regression tests, review screenshot diffs, and manage baselines on a Lastest instance via the @lastest/mcp-server MCP tools.

las-team/lastest · 33 tokens

Lastest design system

Visual + content rules for Lastest, the free open-source visual regression testing platform. Anchored on the Delta Mark logo + 5-stop split-complementary palette.

las-team/lastest · 39 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/mcp-ts-core · 85 tokens

lastest

Lastest is a visual regression testing platform. It records browser tests, runs them via Playwright, diffs screenshots, and uses AI to classify changes. Available as an MCP server for AI agent integration.

las-team/lastest · 0 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/pubmed-mcp-server · 85 tokens