A project-management setup that uses GitHub Issues, GitHub's built-in task and bug tracker, as the authoritative task list for an Obsidian-to-CalDAV project.

It helps create, label, and manage bugs, features, maintenance work, and research tasks for the CalDAV sync project.

It prevents task status from being split across local notes and GitHub, while giving issues consistent priority, area, and type labels.

How josecoelho/obsidian-tasks-caldav configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to josecoelho/obsidian-tasks-caldav. 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/josecoelho/obsidian-tasks-caldav/master/.claude/skills/pm/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/josecoelho/obsidian-tasks-caldav

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/josecoelho/obsidian-tasks-caldav/pm/github.svg)](https://agentmods.dev/skills/josecoelho/obsidian-tasks-caldav/pm)

Your own site

<a href="https://agentmods.dev/skills/josecoelho/obsidian-tasks-caldav/pm"><img src="https://agentmods.dev/badge/skills/josecoelho/obsidian-tasks-caldav/pm/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/josecoelho/obsidian-tasks-caldav/pm"><img src="https://agentmods.dev/badge/skills/josecoelho/obsidian-tasks-caldav/pm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,185 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00016	$0.01185
Opus 5.5	$0.00006	$0.00474
Sonnet 5.5	$0.00003	$0.00237
Haiku 4.5	$0.00002	$0.00119

Measured 2mo ago against content hash 676e69159839, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pm 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 2mo 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.

.claude/skills/pm/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Management — GitHub Issues as Source of Truth

All task state lives in GitHub Issues. Never create local files for tracking (no markdown task files, no local epics, no PRDs). Use gh commands for everything.

Labels

Priority

Label	Use when
`p0-critical`	Data loss, crash, blocks all other work
`p1-high`	Important bug or feature blocking near-term work
`p2-medium`	Should do soon, but not blocking
`p3-low`	Nice to have, do when convenient

Area

Label	Scope
`caldav`	CalDAV client, XML, protocol, VTODO mapping
`sync`	Sync engine, diff logic, adapters, storage
`obsidian-ui`	Settings tab, modals, ribbon, notices
`tasks-plugin`	obsidian-tasks API integration
`infra`	Build, CI, testing infrastructure, tooling

Type

Label	Meaning
`bug`	Something broken
`feature`	New capability
`chore`	Maintenance, refactor, cleanup
`spike`	Research or investigation

Creating Issues

Every issue must include:

Clear title — imperative, concise (e.g., "Handle VTIMEZONE in recurring events")
Description with context on why this matters
Acceptance criteria — bulleted list of what "done" looks like
Testing note — specify which testing approach based on CLAUDE.md:
- E2E test needed — CalDAV protocol, sync round-trips, server quirks
- Unit test needed — pure logic, parsing, mapping
- Manual test needed — Obsidian UI, obsidian-tasks API interactions
Labels — at least one from each category (priority, area, type)

Example:

gh issue create \
  --title "Handle line-folded DESCRIPTION in VTODO responses" \
  --body "$(cat <<'EOF'
## Context
Some CalDAV servers fold long DESCRIPTION lines per RFC 5545. Our parser doesn't unfold them, causing truncated task descriptions.

## Acceptance Criteria
- [ ] VTODO parser unfolds continuation lines (space/tab prefix)
- [ ] Round-trip test: create task with long description, fetch back, verify intact
- [ ] Unit test with fixture for folded DESCRIPTION

## Testing
- E2E test needed (server may fold differently than expected)
- Unit test to lock down the parser fix
EOF
)" \
  --label "bug,p1-high,caldav"

Read the full file on GitHub · 130 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.

2mo ago First seen · 130 lines · 16 tokens per session scan A 676e69159839

Subscribe to this mod's changes

pm is a skill published in the GitHub repository josecoelho/obsidian-tasks-caldav (44 stars, last pushed 24d ago), licensed MIT. It adds 16 tokens to every session and 1,185 once invoked, about $0.0001 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.

Project management

pm next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pmjosecoelho/obsidian-tasks-caldav	Skill	44	24d ago	MIT	A	16	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

obsidian-tasks-caldav: Skill for Claude Code