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 architecture-reviewgit 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/architecture-review)<a href="https://agentmods.dev/skills/assafkip/kipi-system/architecture-review"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/architecture-review/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/architecture-review"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/architecture-review.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 | $0.00105 | $0.00768 |
| Opus 5 | $0.00053 | $0.00384 |
| Sonnet 5 | $0.00021 | $0.00154 |
| Haiku 4.5 | $0.00011 | $0.00077 |
Grade A, and why
architecture-review 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Review Skill
Finds code that is hard to change and proposes a smaller-interface, bigger-
implementation redesign. This is a judgment skill — no paired hook, same
posture as research-mode in skill-hook-pairing.md.
Before running
Read references/deep-module-lens.md. It is the classification lens the
review applies to every module it looks at — do not improvise a different
one.
Scope check (do this first)
This lens is for software modules with interfaces: Python/shell scripts,
plugin code, MCP servers. It does NOT fit markdown rules, canonical files, or
prose content — those don't have "interfaces" in the Ousterhout sense. If the
founder names a target that's mostly .md, say so and ask them to narrow to
a code directory.
Process
- Explore. Spawn an
Agentwithsubagent_type: Exploreover the target directory. Ask it to walk the code and report, per file/module: what it does, its public surface (functions/classes/CLI flags other code calls), and its internal complexity. Don't apply the lens yet — just gather the shape. - Classify with the lens. For each module the Explore pass surfaced,
run the questions in
references/deep-module-lens.md. Flag only modules that are genuinely shallow (interface complexity close to implementation complexity) — a small module with a small interface is fine, not a finding. - Propose, don't prescribe. For each real finding, sketch 1-2 concrete
redesigns using the vocabulary below. State the trade-off of each. Do not
silently pick one — that's a founder/Sana call, same as
quick-plan.md's name-options rule. - Write it up, don't file it. Output goes to
q-system/output/plans/architecture-review-<target-slug>-<YYYY-MM-DD>.md(perquick-plan.md), never a GitHub issue and never auto-filed tospillover— spillover is scoped to findings that interrupt an active PRD/issue's work, andlinear-first.mdalready owns where real work gets tracked. If a finding is worth acting on, the next step is the founder or Sana deciding whether it becomes a Linear issue or aprd-osPRD. - No findings is a valid outcome. Say so plainly if the target directory is already reasonably deep. Don't manufacture friction to justify the run.
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 · 63 lines · 105 tokens per session scan A f25668dd5746
architecture-review is a skill published in the GitHub repository assafkip/kipi-system (110 stars, last pushed 2d ago), licensed MIT. It adds 105 tokens to every session and 768 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 2026-08-30.
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"…
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.
blackboard
Cross-session handoff, persistent context via blackboard, and agent coordination patterns.