Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add assafkip/kipi-system/plugin install kipi-coreWrote 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/commands/assafkip/kipi-system/rca-start)<a href="https://agentmods.dev/commands/assafkip/kipi-system/rca-start"><img src="https://agentmods.dev/badge/commands/assafkip/kipi-system/rca-start.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00015 | $0.00326 |
| Opus 5 | $0.00008 | $0.00163 |
| Sonnet 5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
rca-start 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 8d 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.
What it actually says
Start a root-cause analysis. The author gives a short slug for the failure (e.g.
drawer-empty-code). Default the slug to untitled if none is given.
Process
-
Read the canonical structure from
${CLAUDE_PLUGIN_ROOT}/skills/rca/references/rca-template.md. -
Resolve the output path. Inside a kipi instance use
q-system/output/rca/; in a plain repo userca/. Create the directory:
DIR="q-system/output/rca"; [ -d q-system ] || DIR="rca"; mkdir -p "$DIR"; echo "RCA dir: $DIR"; date +%F
-
Write
<DIR>/rca-<slug>-<YYYY-MM-DD>.mdusing the required structure from the template: metadata (Date, Trigger, Surface-fix commit, Structural-fix commit) and every required##section. Pre-fill Date and anything already known from context. Leave the rest as clearly-marked placeholders. -
Tell the author the file path and that
/rca-check <path>lints it. Do not fill causes or verification you do not actually have; an honest empty section beats an invented one.
The rca-lint hook will validate the file on save. Surface its output verbatim
if it blocks.
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.
- 8d ago First seen · 32 lines · 15 tokens per session scan A 8db86837d4b7
rca-start is a command published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 326 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 commands, from other repositories
diagnostic
Command "diagnostic" from datacore-one/datacore, covering diagnostic, command context, when to reference dip-0002, quick reference and agents this command invokes.
recall
Recall memories with filtering and search.
query
Structured frontmatter queries using yq.
search
Full-text search across all memories.
gc
Garbage collect expired memories.
setup
Configure mnemonic for proactive memory operations.