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 djangonavarro220/agentic-life-os --skill system-improvementgit clone --depth 1 https://github.com/djangonavarro220/agentic-life-osWrote 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/djangonavarro220/agentic-life-os/system-improvement)<a href="https://agentmods.dev/skills/djangonavarro220/agentic-life-os/system-improvement"><img src="https://agentmods.dev/badge/skills/djangonavarro220/agentic-life-os/system-improvement/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/djangonavarro220/agentic-life-os/system-improvement"><img src="https://agentmods.dev/badge/skills/djangonavarro220/agentic-life-os/system-improvement.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 | $0.00029 | $0.01541 |
| Opus 5 | $0.00015 | $0.00771 |
| Sonnet 5 | $0.00006 | $0.00308 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
system-improvement 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
system-improvement
Mandatory integrity contract
Before acting, load and follow ../../references/data-integrity.md. Its provenance, missing-value, correction-history, defensive-write, backup, and recovery rules are mandatory for this subskill.
Improve Life OS itself without turning every annoyance into a refactor. This skill is the system's own feedback loop: inspect how the last period went, identify missing playbooks or broken routines, decide what should become a skill, and propose small safe improvements.
Trigger
Use for:
- system self-improvement reviews
- retrospectives about how Life OS has worked recently
- sprint-review-style summaries of the last week or cycle
- deciding whether repeated work should become a new skill, template, routine, or runtime adapter
- reviewing stale, noisy, missing, or low-value routines
- reviewing heartbeat candidates and deciding which proposed checks deserve to become active watch targets
- reviewing review-item cadence so each recurring check runs daily, weekly, monthly, quarterly, manually, or only on change as appropriate
- maintaining a Life OS improvement backlog
Do not use this for normal user tasks, product hype, or broad rewrites. A good system review produces a small number of concrete improvements, not a manifesto.
Inputs to inspect
Use only configured and approved sources. Useful inputs may include:
- recent Life OS routine run records or pointers
- user feedback captured in runtime-owned memory, tasks, notes, or issue trackers
- repeated manual requests that look like reusable workflows
- doctor warnings, failed cron/routine runs, or stale setup questions
- skill-index gaps and missing playbooks
- public repo issues or local improvement backlog if configured
- private state under
$LIFEOS_DATA_DIR/system-improvement/data.json
Do not copy raw chats, logs, transcripts, or private runtime exports into Life OS state. Store pointers and distilled observations.
Review cadence
Self-improvement is a review item, not necessarily a standalone meeting. It should be included in the normal review-meeting flow when due.
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.
- 11d ago First seen · 159 lines · 29 tokens per session scan A 9a807b1f568e
system-improvement is a skill published in the GitHub repository djangonavarro220/agentic-life-os (11 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 1,541 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…