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 agentmods add skills/rakovi4/continue-framework/rcanpx skills add rakovi4/continue-framework --skill rcagit clone --depth 1 https://github.com/rakovi4/continue-frameworkWhat 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 | $0.00057 | $0.01050 |
| Opus 5 | $0.00028 | $0.00525 |
| Sonnet 5 | $0.00011 | $0.00210 |
| Haiku 4.5 | $0.00006 | $0.00105 |
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 3d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/rca - Root Cause Analysis
Find the real cause of a defect from evidence, not speculation. The deliverable is a cause you have confirmed against real data — logs, test runs, query plans, measurements you actually pulled — recorded in the task spec.md. Producing a plausible-sounding story is the failure mode this skill exists to prevent: a narrative that was never checked against data is a guess, even when it reads like a conclusion.
Input
- target (optional): bugfix task number/slug, or a free-text symptom. If absent, infer from the current task or conversation.
- evidence sources (optional): credentials or paths for authoritative data (CI API, log locations, a reproducible environment). When provided, use them — do not substitute a guess for data you could fetch.
Core Principle
Every prior claim is a hypothesis until you re-verify it here — including claims already written in spec.md, an earlier RCA attempt, a code comment, or this conversation. Carrying a prior hypothesis forward as established fact is the exact failure this skill exists to prevent. Re-derive each claim from primary evidence, or mark it unverified. Distinguish MEASURED (you observed it directly) from REASONED (you inferred it from code plus rules) on every statement, and never present REASONED as MEASURED.
Workflow
-
State the symptom precisely. Pull the exact observable from its authoritative source — the test report, the log line, the failing assertion message — with exact values, units, and frequency, not a paraphrase. For an intermittent failure, get the real pass/fail count and the measured values on both sides of the boundary. Quote the source. Confirm which value the assertion actually checks (it is often not the one a summary reports).
-
Audit prior assumptions. List every claim the existing write-up, prior RCA, comments, or conversation treats as known. For each, record a status — verified (with evidence), refuted (with evidence), or unverified — and reuse no prior conclusion you have not personally re-confirmed.
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.
- 3d ago First seen · 51 lines · 57 tokens per session scan A cdbc35fa51f3
rca is a skill published in the GitHub repository rakovi4/continue-framework (50 stars, last pushed 6d ago), licensed MIT. It adds 57 tokens to every session and 1,050 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…