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 assafkip/kipi-system --skill improvegit clone --depth 1 https://github.com/assafkip/kipi-systemWrote 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/assafkip/kipi-system/improve)<a href="https://agentmods.dev/skills/assafkip/kipi-system/improve"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/improve.svg" alt="Measured on agentmods" 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 | $0.00098 | $0.00735 |
| Opus 5 | $0.00049 | $0.00367 |
| Sonnet 5 | $0.00020 | $0.00147 |
| Haiku 4.5 | $0.00010 | $0.00073 |
Grade A, and why
improve 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve: an outside idea, judged against the system that exists
Plan item 2d of the morning-brief overhaul (Bloom's improve pass). The
founder pastes an idea. This skill answers one question: does it change how
the SYSTEM works, and is that change already here?
The two halves
-
Deterministic (this skill must run it, never reason from memory):
python3 plugins/kipi-core/skills/improve/scripts/improve_ground.py --target <rule|lint|hook|trigger|context|skill|prompt|test|script|job> "<idea in one sentence>"It prints a JSON verdict with
cites(lessons paths or named files) and acorporareport saying which lessons directories were read, missing or unreadable. Exit 0 foralready-built/adopt, 2 forskip. SetKIPI_LESSONS_CORPORA=/path/one:/path/twoto ground against more than this instance's corpus; the report names each one either way. -
Judgment (the skill): read what the script cited. Then write the critique in this shape:
- The idea, in one sentence, as a SYSTEM change (a stage, a trigger, a rule, a context entry). If it cannot be phrased that way it is roadmap, and the verdict is skip regardless of how good the idea is.
- What already exists: the cited file or lesson, opened, with the line that covers it. Not "we have something like that".
- Verdict:
already-built(name the file),adopt(name the smallest change and the check that would prove it), orskip(name the reason the classifier gave).
Hard constraint
This skill fixes the system. It never decides the roadmap. An idea about what
to build, sell, price, publish or advise a client returns skip from the
script (roadmap_scope.py, fail-closed on unknown) and the skill does not
override that with judgment. If the founder wants the product conversation,
that is a conversation, not this skill.
Do not
- Cite from memory. If the script's
citesis empty the verdict is not a verdict; say so. - Widen the trigger. This is on-demand only; it never rides the brief or the weekly pass.
- Read a corpus the report says is missing. Say it is missing.
What ships with it
2 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.
- 4d ago First seen · 56 lines · 98 tokens per session scan A bbf6997439bd
improve is a skill published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 735 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
tutorial
Interactive walkthrough for new users. Learn by doing — each step creates real content in your vault. Three tracks (researcher, manager, personal) with a universal learning arc. Triggers on "/tutorial", "walk me through", "how do I use this".
learn
Research a topic and grow your knowledge graph. Uses Exa deep researcher, web search, or basic search to investigate topics, files results with full provenance, and chains to processing pipeline. Triggers on "/learn", "/learn [topic]", "research this", "find out about".
core
This skill should be used when the user says "capture memory", "save to memory", "remember this", or trigger phrases like: "I've decided", "let's use", "we're going with", "I learned", "turns out", "TIL", "discovered", "I'm stuck", "blocked by", "always use", "never do", "convention is". Also triggers on recall…
custodian
Memory system custodian for health checks, validation, and maintenance. Trigger phrases: "check memory health", "validate memories", "fix broken links", "update decay", "relocate memories", "audit memories", "memory maintenance", "custodian", "memory health".
format
MIF Level 3 specification, memory templates, and formatting guidelines.
ontology
Ontology-based entity discovery and validation for mnemonic memories. Define custom namespaces, entity types, traits, and relationships. Triggers: "entity discovery", "validate ontology", "define namespaces", "resolve entity references", "list ontologies", "show namespaces", "entity types", "entity relationships"…