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 rcagit 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/rca)<a href="https://agentmods.dev/skills/assafkip/kipi-system/rca"><img src="https://agentmods.dev/badge/skills/assafkip/kipi-system/rca.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 | $0.00100 | $0.00806 |
| Opus 5 | $0.00050 | $0.00403 |
| Sonnet 5 | $0.00020 | $0.00161 |
| Haiku 4.5 | $0.00010 | $0.00081 |
Grade A, and why
rca 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 9d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RCA Skill
The diagnostic counterpart to forward planning. When a failure gets past a test, a gate, or review, write a root-cause analysis to the canonical template. The goal is never who, it is: what guardrail was missing and why the mistake was easy to make.
Before writing
Read references/rca-template.md. It is the canonical structure and the exact
contract the lint enforces. Do not improvise a different shape.
When to write an RCA
- A defect shipped and a human or a gate caught it after the fact.
- A run came back BLOCKED, or a deliverable failed validation.
- A bug recurs after a prior fix (the prior fix treated a symptom).
- The user says "rca this", "root cause this", "postmortem this", "why did this break".
A trivial bug you fix in the same breath, that never escaped a gate, does not need an RCA. A failure that got past a test, a gate, or review does.
Where RCAs land
q-system/output/rca/rca-<slug>-<YYYY-MM-DD>.md inside a kipi instance, or
rca/rca-<slug>-<YYYY-MM-DD>.md in a plain repo. The lint fires on any file
named rca-*.md / premortem-*.md or any doc whose H1 starts with # RCA: or
# Premortem.
The rules the lint enforces
- Surface vs structural root cause. Surface is the trigger (what fired). Structural is the latent systemic cause (why it was allowed and went uncaught).
- Multi-factor. Use
### Root cause #1,### Root cause #2when more than one structural cause contributed. Resist a single tidy cause. - Cause-type tags. Each structural cause carries a
type:line, one of: code-defect, config, environmental-trigger, missing-test, implicit-contract, process, capacity. - Verification is evidence. Show the command and result ("ran X, got Y") or the passing test. An assertion with no observed output is not verification.
- Action items are checkboxes with owners. Not prose. An RCA is not finished until its actions are owned and trackable.
- Blameless. Describe system, contract, gate, and test failures. Never name a person as the cause.
What ships with it
4 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.
- 9d ago First seen · 67 lines · 100 tokens per session scan A f5d3e090d77a
rca is a skill published in the GitHub repository assafkip/kipi-system (110 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 806 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.