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.
git clone --depth 1 https://github.com/vincentmumme/personalos-boilerplatenpx agentmods add skills/vincentmumme/personalos-boilerplate/write-skillWrote 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/skills/vincentmumme/personalos-boilerplate/write-skill)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.01735 |
| Opus 5 | $0.00039 | $0.00868 |
| Sonnet 5 | $0.00016 | $0.00347 |
| Haiku 4.5 | $0.00008 | $0.00173 |
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.
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
nameanddescription, plus the closedpos_*record namespace insidemetadata. pos_createdandpos_updatedare emitted as quoted ISO-date strings so YAML loaders cannot turn them into non-JSON-serializable date objects during Runtime-Agent skill loading.namematches the lower-kebab skill folder and is not duplicated ascapability_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_keysdescribes POS-record writes only and always haspos_check_refs. External side effects are explained in the body and are not collapsed into a genericmutatingfield.- 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.mdand representativerouting-eval.jsonlcases. - Every write is validated against the runtime contract, the
pos-v1Registry, resolver health and the explicit POS postflight.
Workflow
- Confirm scope and ownership.
Read the request,
skills/RESOLVER.md,skills/index.mdand the closest existing skills. If the workflow is still only a candidate, route toskillify. If it belongs to one repository or one agent, keep it at that narrower owner unless {{user_name}} explicitly requests a shared POS skill.
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.
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.
- 9d ago First seen · 119 lines · 78 tokens per session scan A 109e748a4d00
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.
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".
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.
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.
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…
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]".
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".