write-skill

write-skill is a skill for Claude Code, Codex from vincentmumme/personalos-boilerplate. It costs 78 tokens per session (1,735 once invoked), scanned A, original, MIT.

A skill for creating or revising shared PersonalOS skills. It defines the required file structure and checks that a new skill does not duplicate an existing capability.

In plain words
What is it for?
Writing one shared skill under skills/ or updating a specified shared skill when its purpose and scope are already clear.
Why use it?
It reduces inconsistent skill formats, duplicated instructions, and metadata errors that can stop skills from being discovered or loaded correctly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 system/data-model/scripts/pos_v1.py validate --files skills/<name>/SKILL.md.

Good fit Writing one shared skill under skills/ or updating a specified shared skill when its purpose and scope are already clear.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/vincentmumme/personalos-boilerplate
agentmods
npx agentmods add skills/vincentmumme/personalos-boilerplate/write-skill

Made for: Claude Code, Codex.

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 write-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/vincentmumme/personalos-boilerplate/write-skill/github.svg)](https://agentmods.dev/skills/vincentmumme/personalos-boilerplate/write-skill)
Your own site
<a href="https://agentmods.dev/skills/vincentmumme/personalos-boilerplate/write-skill"><img src="https://agentmods.dev/badge/skills/vincentmumme/personalos-boilerplate/write-skill/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.

agentmods 80×15 button for write-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/vincentmumme/personalos-boilerplate/write-skill"><img src="https://agentmods.dev/badge/skills/vincentmumme/personalos-boilerplate/write-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,735 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00078 $0.01735
Opus 5 $0.00039 $0.00868
Sonnet 5 $0.00016 $0.00347
Haiku 4.5 $0.00008 $0.00173

Measured 9d ago against content hash 109e748a4d00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

write-skill 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 9d 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.

core/skills/write-skill/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: write-skill

Purpose

Create or revise one shared PersonalOS skill without inventing a second skill format, duplicating system rules inside the skill, or breaking runtime discovery. SKILL.md remains the single canonical skill record; scripts/, references/ and assets/ are optional local execution resources rather than companion truth records.

Contract

This skill guarantees:

  • A MECE check happens before a new skill folder is created. Extend an existing capability when it already owns the intent.
  • The host runtime's authoritative skill-authoring guidance is followed for discovery, instruction quality and resource design.
  • Every shared PersonalOS skill uses the runtime envelope from [[system/templates/skill]]: top-level name and description, plus the closed pos_* record namespace inside metadata.
  • pos_created and pos_updated are emitted as quoted ISO-date strings so YAML loaders cannot turn them into non-JSON-serializable date objects during Runtime-Agent skill loading.
  • name matches the lower-kebab skill folder and is not duplicated as capability_key.
  • POS integration is declared only when present. No empty pos_system_refs, I/O, template, invocation or check lists are written.
  • pos_writes_profile_keys describes POS-record writes only and always has pos_check_refs. External side effects are explained in the body and are not collapsed into a generic mutating field.
  • Persisted POS-record shapes and general POS semantics come from /system; skill-local resources contain only execution-specific scripts, references, prompts, examples, fixtures or assets.
  • New routable skills are connected to skills/RESOLVER.md, skills/index.md and representative routing-eval.jsonl cases.
  • Every write is validated against the runtime contract, the pos-v1 Registry, resolver health and the explicit POS postflight.

Workflow

  1. Confirm scope and ownership. Read the request, skills/RESOLVER.md, skills/index.md and the closest existing skills. If the workflow is still only a candidate, route to skillify. If it belongs to one repository or one agent, keep it at that narrower owner unless {{user_name}} explicitly requests a shared POS skill.

Read the full file on GitHub · 119 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 119 lines · 78 tokens per session scan A 109e748a4d00

Subscribe to this mod's changes

write-skill is a skill published in the GitHub repository vincentmumme/personalos-boilerplate (17 stars, last pushed 14d ago), licensed MIT. It adds 78 tokens to every session and 1,735 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.

Related

Other skills, from other repositories

lint-brain

Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".

michaeljauk/brain-starter · 56 tokens

ingest-article

Ingest an article from a URL or raw text into the brain vault. Extracts key knowledge, determines placement, creates or updates notes, and links to relevant projects. Use when the user shares a URL or text and wants to absorb it into their knowledge base.

michaeljauk/brain-starter · 58 tokens

wrap-session-up

End-of-session review for a Claude Code conversation. Replays what was discussed, checks for open action items, documents relevant outcomes in the brain vault, and creates Todoist tasks for anything untracked. Use at the end of a work session to ensure nothing falls through the cracks.

michaeljauk/brain-starter · 60 tokens

kickoff

Guided first-run setup for a forked brain-starter vault. Walks through identity, first project, semantic search, integrations, indexes, and the first commit - verifying each phase before moving on. Use when the user has just forked or cloned brain-starter, says "set up my brain", "I just forked brain-starter", or runs…

michaeljauk/brain-starter · 80 tokens

project-sync

On-demand AI-powered sync of a project's repo state into the brain vault. Reads live git/GitHub/Jira data, updates the project status doc, and makes targeted edits to relevant brain docs where content is clearly stale. Triggered by "/project-sync [name]", "sync [project]", "what's the current state of [project]".

michaeljauk/brain-starter · 73 tokens

research-spike

Research a topic using /last30days community signals, then produce a structured comparison matrix and recommendation note in the brain vault. Use when evaluating tools, libraries, vendors, or approaches — e.g. "spike on auth providers", "research X vs Y", "evaluate options for Z".

michaeljauk/brain-starter · 63 tokens