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 skills add vincentmumme/personalos-boilerplate --skill pos-verifygit clone --depth 1 https://github.com/vincentmumme/personalos-boilerplateWrote 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/pos-verify)<a href="https://agentmods.dev/skills/vincentmumme/personalos-boilerplate/pos-verify"><img src="https://agentmods.dev/badge/skills/vincentmumme/personalos-boilerplate/pos-verify/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/pos-verify"><img src="https://agentmods.dev/badge/skills/vincentmumme/personalos-boilerplate/pos-verify.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 | $0.00065 | $0.02518 |
| Opus 5 | $0.00032 | $0.01259 |
| Sonnet 5 | $0.00013 | $0.00504 |
| Haiku 4.5 | $0.00006 | $0.00252 |
Grade A, and why
pos-verify 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 11d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: pos-verify
System dependencies: [[system/contracts/core/personalos-mutation-contract]], [[system/checks/core/personalos-mutation-postflight]], [[system/contracts/core/capability-interface]] und [[system/frameworks/core/verification-ownership]]. Bulk guard: [[system/runbooks/core/test-before-bulk]].
Contract
This skill guarantees:
- Verification is write-scoped: it checks files changed in the current run plus the propagation map and any adjacent no-op targets needed to validate routing.
- Verification is both semantic and deterministic. The script is a baseline, not the whole review.
- Every static Finding Code emitted by the runner is mapped to exactly one declarative Check owner; the mapping test blocks silent unmapped additions or removals.
- The new truth, source/evidence, target owner, section placement, provenance, Current Truth synthesis, State/Open Threads, Timeline behavior, and no-op decisions are checked against the relevant conventions.
- Explicit file lists from the owning writer are preferred over Git discovery.
- The runner resolves the owning PersonalOS vault from its own installed script path before consulting the caller's working directory, so absolute invocations outside the vault do not turn valid wikilinks into false broken-link warnings.
- Git-diff fallback is available when no explicit file list exists, but large dirty trees are flagged as unreliable.
- Findings return
pass,warn, orfailwith file-level remediation. pos-gbrain-v1files are checked against their profile: person, company, deal, project, program, source, or automation-output.- Files declaring
schema_version: pos-v1are resolved throughsystem/data-model/registry.yamland checked for the six-field Foundation, UUIDv7 identity, registered Primary Profile, field ownership, types/enums, path, Page Shape sections, conditional state rules, typed relations, Title/H1 equality and duplicate IDs. - Changes to the canonical data-model Registry fail when generated Field-/Profile-Indizes or per-profile JSON Schemas drift; generated artifacts are rebuilt from the Registry and never edited independently.
- Explicit interaction scan reports under
_system/runs/withtype: sourceandrole: run-reportkeep the source profile even though they live beside automation artifacts; dated producer outputs underautomations/*/outputs/use the automation-output profile. - Person/company quality checks warn when Current Truth exceeds 500 words; project/deal/program checks warn above 400 words. All five canonical entity/work profiles warn when State exceeds 12 bullets or Open Threads exceeds 10 bullets; project pages also warn on checkbox-based shadow task lists. These are rewrite/routing warnings, not permission to delete material truth.
- Day Records, Activity Contributions and Journal Entries are checked exclusively through their registered
pos-v1profiles.pos-verifydoes not duplicate Daily fields or templates. - Deep vault-wide drift remains owned by
system-health-check.
What ships with it
3 files 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.
- 11d ago First seen · 125 lines · 65 tokens per session scan A b1120af8e7ce
pos-verify is a skill published in the GitHub repository vincentmumme/personalos-boilerplate (19 stars, last pushed 16d ago), licensed MIT. It adds 65 tokens to every session and 2,518 once invoked, about $0.0003 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
test-gates
A workflow for running and reporting software quality checks, including code checks, tests, smoke checks, and flaky-test notes.
agentic-engineering
Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable state, and verified write-back.
verify-before-claim
Use when an agent is about to claim completion, correctness, safety, publication, deployment, or any consequential external fact.
tt
Quality gate immediately after building: prove that what was just built actually works, while the context is still hot. Six steps: scope what changed, run live on real data, break it on purpose, show a counter or log proving it ran, root-cause any failure and re-run, then a verdict with evidence. Only a green verdict…
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.