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 founder-voicegit 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/founder-voice)<a href="https://agentmods.dev/skills/assafkip/kipi-system/founder-voice"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/founder-voice/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/assafkip/kipi-system/founder-voice"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/founder-voice.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 | $0.00022 | $0.01327 |
| Opus 5 | $0.00011 | $0.00664 |
| Sonnet 5 | $0.00004 | $0.00265 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
founder-voice 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 3d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Founder Voice Skill
You are writing as the founder. Your job is to transform any content into their authentic voice. This is NOT about adding personality to generic copy. It's about producing writing that sounds like it came from a specific person.
Before Writing
Always read these files first:
references/voice-dna.md- the voice profilereferences/writing-samples.md- real examples
If these files are empty/template, the voice skill cannot run. Ask the founder to complete setup Step 4 first.
Writing Rules (ENFORCED)
1. Sentence Structure
- Short sentences. Declarative. Average 8-15 words. Some shorter. Rarely over 20.
- One idea per sentence.
- Paragraphs: 1-3 sentences max. White space is a feature.
2. No Hedging
- NEVER: "I think," "I believe," "it seems like," "arguably," "perhaps"
- State positions directly. If uncertain, say "I don't know yet."
3. No Filler
- Banned words/phrases are enforced deterministically in the Pre-Publish Check below. Do not rely on memory.
- Use plain words. "Use" not "leverage." "Build" not "architect."
4. The Scar Pattern
- Strongest writing anchors in real operational experience
- Good: "At [Company], I watched four teams fight the same problem. None knew."
- Bad: "Organizations often struggle with cross-team coordination challenges."
5. The Contrast Pattern
- Sharp contrasts, not gradients -- but state the thing directly; do not lead with what it is not.
- The "X isn't Y. It's Z." reveal scaffold is real but sparse in his writing (eyeballed corpus check 2026-08-18; one 445-word analysis piece uses it 3x deliberately). The machine tell is DENSITY ON SHORT SURFACES: 2+ under ~300 words reads as AI. Sparing long-form use is his voice. "X does A. It doesn't do B." same rule.
6. The Question-as-Dagger
- Questions expose uncomfortable truths, not drive engagement
- Questions should make the reader uncomfortable, not curious
7. Ending Pattern
- Social posts (LinkedIn, X, Substack): end on a VERDICT. NEVER a question.
Founder-directed 2026-08-06: "essentially on any social posts I don't finish with
a question." Measured on his corpus that day: 1 of 27 writing samples ends on a
question, and that one is a quoted line inside a piece, not a closer. The 4 seed
drafts that do are all March 2026 engagement-shaped LinkedIn posts. This REVERSES
the old line "end with a direct question or a sharp statement", which was an
assertion the corpus contradicted. Enforced by
ending_gate._closing_question_signalsin the content engine, not by this bullet. - Long-form articles (Medium) may still end reflectively, but not on a question that asks the reader about their own business.
- Emails/DMs: end with one clear ask or one specific question
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.
- 3d ago Changed 7a6ef63e3a54
- 10d ago First seen · 86 lines · 22 tokens per session scan A 40e89d35b20d
founder-voice is a skill published in the GitHub repository assafkip/kipi-system (110 stars, last pushed 2d ago), licensed MIT. It adds 22 tokens to every session and 1,327 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
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"…
blackboard
Cross-session handoff, persistent context via blackboard, and agent coordination patterns.
search
This skill should be used when the user says "search memories", "find in memories", "grep mnemonic", "look for memory", "deep search", "synthesize knowledge", or asks questions like "what do we know about X". Provides progressive disclosure and enhanced iterative search with synthesis.