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 councilgit 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/council)<a href="https://agentmods.dev/skills/assafkip/kipi-system/council"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/council/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/council"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/council.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 | $0.00895 |
| Opus 5 | $0.00011 | $0.00447 |
| Sonnet 5 | $0.00004 | $0.00179 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
council 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council
Multi-agent debate for founder decisions. 4 personas argue a topic across structured rounds, respond to each other's actual points, then synthesize. Produces a visible transcript and a recommended path.
When to Use
Invoke when:
- Conflicting signals from conversations and you need to decide which to follow
- About to change positioning in canonical files (
/q-calibrate) - Design partner asks for something that might pull you off-wedge
- Investor feedback contradicts buyer feedback
- Competitive move detected and you need a response strategy
- Any decision where "it depends" means you need structured tension
- User says "council", "debate this", "weigh options", "get perspectives"
Workflow Routing
| Trigger | Workflow | Time |
|---|---|---|
| Full structured debate (3 rounds) | workflows/debate.md |
30-90 sec |
| Quick sanity check (1 round) | workflows/quick.md |
10-20 sec |
Default to Quick. Use Debate only for positioning changes, pre-investor prep, or decisions that affect canonical files.
The Personas
4 personas, each anchored to real project files. They read the files before speaking -- grounded opinions, not generic advice.
| Persona | Perspective | Reads | Core Question |
|---|---|---|---|
| Operator | What we can actually do today | q-system/my-project/current-state.md |
"Can we ship this with what we have?" |
| Buyer | What a CISO/security leader would pay for | q-system/canonical/discovery.md, q-system/my-project/relationships.md |
"Would a buyer pay for this? Does it match what they asked for?" |
| Investor | The fundable narrative | q-system/canonical/talk-tracks.md |
"Does this sharpen or dilute the story?" |
| Contrarian | What's wrong, what we're not seeing | q-system/canonical/objections.md, q-system/my-project/competitive-landscape.md |
"What breaks? What are we ignoring?" |
Persona Rules
- Every persona speaks from their anchored files, not from general knowledge
- If a canonical file is empty/template, the persona says "I don't have data to ground this" -- no guessing
- Personas reference specific entries from their files when making points
- Contrarian must raise at least one uncomfortable point per round
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.
- 10d ago First seen · 87 lines · 22 tokens per session scan A f4e98251fb71
council is a skill published in the GitHub repository assafkip/kipi-system (110 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 895 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…
blackboard
Cross-session handoff, persistent context via blackboard, and agent coordination patterns.
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"…
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.