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 FlorinI/Florians-Claude-Code-Kit --skill rcagit clone --depth 1 https://github.com/FlorinI/Florians-Claude-Code-KitWrote 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/florini/florians-claude-code-kit/rca)<a href="https://agentmods.dev/skills/florini/florians-claude-code-kit/rca"><img src="https://agentmods.dev/badge/skills/florini/florians-claude-code-kit/rca/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/florini/florians-claude-code-kit/rca"><img src="https://agentmods.dev/badge/skills/florini/florians-claude-code-kit/rca.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00174 | $0.01177 |
| Opus 5.5 | $0.00070 | $0.00471 |
| Sonnet 5.5 | $0.00035 | $0.00235 |
| Haiku 4.5 | $0.00017 | $0.00118 |
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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Root Cause Analysis
When something is broken, the cheap and tempting move is to name the first plausible cause and fix it. That is the single most common way root-cause analysis goes wrong, and it is precisely the failure mode of a fluent model: producing a confident, well-argued, wrong cause. The entire job of this skill is to make one habit automatic on every path — state what would prove the hypothesis wrong, then go check before touching the fix. Everything else is just how much rigor to spend on the writeup.
On invocation: triage the depth, then proceed (do not ask)
The moment this skill triggers, choose a depth from the context you already have. Do not interrogate the user with a stakes questionnaire — that ceremony is exactly what this skill is designed to avoid, and it taxes the common (cheap) case hardest. Infer the stakes, announce your choice in one sentence, and proceed. The user keeps a veto either way.
Default to the light path. Escalate to the heavy path if any of these hold:
- The fix or finding gates an expensive or hard-to-reverse decision — schema migration, data backfill, system rebuild, pricing or contract change, an irreversible deploy.
- It touches a high blast-radius surface — auth, payments, money movement, data deletion, security, privacy.
- It is a recurring or repeat failure, or a whole class of bug, not a one-off.
- The user asked for a written / full / documented RCA.
Honor explicit overrides in both directions. "Quick diagnosis" or "just fix it" means light even when signals are present — if you think that's genuinely risky, say so in one line and then proceed as asked. "Full RCA" or "write it up" means heavy.
Announce in one line, then go. Don't wait for a reply. For example:
- "Low-stakes and reversible, so I'll do a quick diagnosis. Say 'go deep' if you want the full RCA."
- "This gates the migration, so I'll do a full documented RCA."
- "You asked for the writeup, proceeding heavy."
One more rule that holds on both paths: do not narrate the steps as you work ("now doing Step 4..."). The user should see the observation, the check, and the fix — never the machinery. The steps below are internal scaffolding for you, not a script to read aloud.
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.
- 1mo ago First seen · 56 lines · 174 tokens per session scan A d07b3509596e
rca is a skill published in the GitHub repository FlorinI/Florians-Claude-Code-Kit (5 stars, last pushed today), licensed MIT. It adds 174 tokens to every session and 1,177 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
atomic-debug
Hypothesis-driven debugging skill. Use when a bug, test failure, crash, or unexpected behavior is reported. Auto-trigger on error pastes or "broken/doesn't work/failing" language. Explicit invocation: /atomic-debug. Output: symptom statement → hypothesis table → cheapest test first → root cause. No symptom-patching.…
sipcode-regress
Check the user's own local Claude Code and Codex logs for regressions after an update (prompt-cache misses, 5-minute cache TTL, uncached context, hourly cache rebuilds, Codex usage limit draining faster per token) and pin each one to the version that introduced it, using the Sipcode CLI. Use when the user asks whether…
ralphctl-debugging-and-error-recovery
Systematic root-cause debugging. Use when tests fail, builds break, something that worked before broke, or behaviour does not match expectations — when you need to figure out what broke and why. Follow stop-the-line → reproduce → localize → reduce → root-cause → guard-with-regression-test → verify, not guessing; the…
ralphctl-code-simplification
Behaviour-preserving simplification of existing code — understand why the code exists before changing it, then reduce nesting, unclear names, duplication, dead code, and needless indirection one step at a time with the existing tests unchanged and green after each. Use when a task asks to refactor or clean up working…
system-health
Suggest whether the machine needs a DISK or MEMORY cleanup — and catch the case where Heimdall ITSELF is the hog (runaway orphaned python from the presence keeper). Use when the machine is slow / swapping / laggy, disk or "System Data" is full, memory is exhausted, at the start of a long session, or when the user asks…
debug-my-harness
Diagnose why an agent harness misbehaved by reading the local flight-recorder ledger (.vigiles/runs.jsonl) — which skills fired or got hijacked, which hooks blocked or wrongly allowed, which subagent tool-contract violations happened, and how a skill's trigger rate moved. Use when asked why a skill stopped firing, why…