Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/musingfox/cc-plugins/pmnpx skills add musingfox/cc-plugins --skill pmgit clone --depth 1 https://github.com/musingfox/cc-pluginsWhat 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 | $0.00077 | $0.01320 |
| Opus 5 | $0.00039 | $0.00660 |
| Sonnet 5 | $0.00015 | $0.00264 |
| Haiku 4.5 | $0.00008 | $0.00132 |
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 yesterday.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pm — Obsidian Project Management
Run the obsidian CLI directly — no sub-agent. Before any CLI call, invoke the obsidian:obsidian-cli skill to load exact syntax — never run obsidian help/--help to discover it. This skill owns only the PM conventions: folder layout, template names, property schema, ADR numbering, and dashboard generation.
CLI gotcha: file= resolves like a wikilink — bare note name only, no path, no .md. Use path= for vault-root-relative paths. If a command returns File not found after a create, fix the parameter — never re-run create (it makes name 1.md duplicates).
property:set gotcha: one property per call, no batch form. Pass type=list for tags, type=date for due/completed — omit type= and it's stored as plain text.
Config (.obsidian.yaml)
vault: <VAULT_NAME>
pm:
project: <PROJECT_NAME>
Missing config or pm.project → tell the user to run /obw:init and stop. Never guess the vault.
Vault Layout
pm/
├── {project}/
│ ├── tasks/ # active tasks
│ ├── archive/ # completed tasks
│ └── docs/ # docs + ADRs
└── dashboard.base # cross-project dashboard (optional)
Folders are created on demand — create / move auto-create missing parent folders. No mkdir needed.
Template Names
Fixed: task, doc, adr. Installed into the vault's Obsidian Templates folder by /obw:init. Use via CLI create template=<name>.
If obsidian vault=<v> templates doesn't list one of these, /obw:init hasn't run (or the user removed them). Tell the user to re-run init rather than inlining template content here.
Operations
Use one call per known-name read — never chain search → read. The pm-specific bits:
- Create task →
createatpm/{project}/tasks/{name}.mdwithtemplate=task, then set propertiesproject/priority/due/tags. - Create doc →
createatpm/{project}/docs/{name}.mdwithtemplate=doc, then setproject. - Create ADR →
createatpm/{project}/docs/adr-{NNNN}-{title}.mdwithtemplate=adr, then setproject/status. See ADR numbering below. - List tasks →
searchwithquery="[type:task] [project:{project}] [status:<s>]" format=json. - Archive → set
status=doneandcompleted, thenmovetopm/{project}/archive. - Delete → confirm first; fall back to
moveif the build lacksdelete.
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.
- yesterday First seen · 93 lines · 77 tokens per session scan A 1ebcf9516afe
pm is a skill published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 1,320 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…