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 loggit 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/log)<a href="https://agentmods.dev/skills/vincentmumme/personalos-boilerplate/log"><img src="https://agentmods.dev/badge/skills/vincentmumme/personalos-boilerplate/log/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/log"><img src="https://agentmods.dev/badge/skills/vincentmumme/personalos-boilerplate/log.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00059 | $0.02786 |
| Opus 5 | $0.00030 | $0.01393 |
| Sonnet 5 | $0.00012 | $0.00557 |
| Haiku 4.5 | $0.00006 | $0.00279 |
Grade A, and why
log 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 10d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: log
Contract
This skill guarantees:
- Useful residue from an agent session is persisted as an Activity Contribution, an optional Journal Entry, or both, and when safe as concise updates to affected canonical owner files.
/logis a write-back command by default, not a proposal command. Draft mode is used only when {{user_name}} asks for it or when a risky mutation cannot be skipped safely.- Der Day Record bleibt der kompakte zeitliche Querschnitt. Activity Contributions belegen materielle Arbeit oder Wirkung; Journal Entries bewahren persönliche Gedanken und Reflexion. Keiner dieser Records wird zur parallelen Projekt- oder Domainwahrheit.
- Die Record-Formate werden ausschließlich von den registrierten Profilen
day-record,activity-contributionundjournal-entrysowie den Vorlagen untersystem/templates/daily/bestimmt. Dieser Skill besitzt keine eigene Daily-Vorlage. - Concrete tasks, decisions, checks, waiting states, and reassessment needs are routed through
task-managerinto the atomic Action/Attention records underoperations/. - Durable project, person, company, deal, finance, content, skill, automation, or interaction truth is updated only in the appropriate owner file and only when the session creates a high-confidence delta.
- Process-friction or useful-pattern signals are im passenden Daily-Record belegt und zum owning Skill,
task-managerodersystem-health-checkgeroutet, wenn sie handlungsrelevant sind. Keine separate Feedback-Queue wird erzeugt. - Knowledge candidates are marked for later knowledge skills; this skill does not mix operative PersonalOS truth into knowledge-topic pages.
- Write boundary: this skill may create
daily/YYYY/YYYY-MM-DD/activity/<uuid>.md,daily/YYYY/YYYY-MM-DD/journal/<uuid>.md, assemble the matching Day Record, update atomic Action/Attention records viatask-manager, update affected owner files, and update a skill/reference/template/script only when {{user_name}} explicitly asked for that change in the current session. - Capture boundary: when a session contains unresolved but materially valuable input that cannot yet be routed safely, this skill may create one atomic
captureunderinbox/captures/<uuid>.mdfrom the registered profile and template. It does not mirror the full chat or create a general Idea Record. - Approval boundary: creating new durable owner records beyond the bounded Capture allowed above, changing identity/relationship/legal/tax/pricing/strategy/finance truth, deleting/moving existing owner files, resolving contradictions, or writing raw private/sensitive material requires explicit approval or is recorded as an unresolved point. The Capture exception never authorizes a new permanent domain owner.
- Every new durable claim gets provenance through die atomare Activity/Journal-Evidenz, inline source,
Source Map, provided source path, or explicit {{user_name}} statement. - All PersonalOS mutations follow [[system/contracts/core/personalos-mutation-contract]] and finish with
pos-verifyon the explicit changed-file list. - New and materially revised PersonalOS prose is written in German. Existing English records are not bulk-translated; when they are materially rewritten, consolidate the affected living truth in German. Source material retains its natural language. See 2026 08 07 sprache deutsch intern.
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.
- 10d ago First seen · 138 lines · 59 tokens per session scan A 603895e0e844
log is a skill published in the GitHub repository vincentmumme/personalos-boilerplate (17 stars, last pushed 15d ago), licensed MIT. It adds 59 tokens to every session and 2,786 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
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]".
save-answer
File a conversation output (research, analysis, comparison, framework) back into the brain vault so it compounds instead of vanishing into chat history. Use when the user says "save this", "file this", "keep this", or when a valuable answer should persist.