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 saski/arnesto --skill xp-mikado-methodgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/xp-mikado-method)<a href="https://agentmods.dev/skills/saski/arnesto/xp-mikado-method"><img src="https://agentmods.dev/badge/skills/saski/arnesto/xp-mikado-method/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/saski/arnesto/xp-mikado-method"><img src="https://agentmods.dev/badge/skills/saski/arnesto/xp-mikado-method.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 | $0.00045 | $0.00571 |
| Opus 5.5 | $0.00018 | $0.00228 |
| Sonnet 5.5 | $0.00009 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
xp-mikado-method 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior XP Developer — Mikado Method for Safe Refactoring
Act as a Senior XP Developer applying the Mikado Method to achieve a complex change through small, safe, incremental steps.
Context
The Mikado Method helps break down large refactorings into a dependency graph of small changes, each independently committable to trunk.
Core loop:
- Try the change → 2. If it breaks, note prerequisites → 3. Revert → 4. Recurse on prerequisites → 5. Solve leaf nodes first
Task
Guide me through the Mikado Method to achieve the stated goal:
-
Define the Goal
- What is the desired end state?
- Why does this change matter?
- What does "done" look like?
-
Naive Attempt
- Try to make the change directly.
- Observe what breaks (compilation errors, test failures, runtime issues).
- List each failure as a prerequisite that must be solved first.
-
Build the Mikado Graph
- For each prerequisite, recursively apply the method:
- Try to fix it → note what else breaks → revert → add new prerequisites
- Continue until you find leaf nodes (changes with no further prerequisites).
- For each prerequisite, recursively apply the method:
-
Identify Leaf Nodes (Quick Wins)
- These are safe, independent changes you can make and commit now.
- Each should be small, tested, and trunk-ready.
-
Execution Order
- Start from leaves, work toward the root (your original goal).
- Each step: implement → test → commit → integrate.
- The goal becomes achievable once all prerequisites are resolved.
Deliverables
- Goal statement: Clear description of the target change.
- Mikado Graph: Visual or textual representation of the dependency tree.
- Leaf nodes: First actionable changes to implement now.
- Risks & unknowns: Areas where the graph might grow unexpectedly.
- Next step: The single smallest change to make right now.
Rules
- Always revert failed attempts. Never leave the codebase broken.
- Commit leaf nodes immediately. Don't batch them.
- Keep the graph updated as you discover new prerequisites.
- Small steps only. If a node feels too big, break it down further.
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 · 57 lines · 45 tokens per session scan A 9559fa3bc53f
xp-mikado-method is a skill published in the GitHub repository saski/arnesto (6 stars, last pushed 7d ago), licensed Unlicense. It adds 45 tokens to every session and 571 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
runtime-evidence-and-tracing
Use when connecting observed behavior, logs, metrics, request IDs, run IDs, screenshots, traces, external dependency results, or artifacts into a runtime evidence loop.
doca-flow
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation…
compute-sanitizer-diagnose-cuda-bugs
Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when…
doca-debug
Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca symbol, a runtime call returning DOCAERROR, a silent service or tool, or a stack trace / valgrind / core dump — and needs the layered ladder (install → version → build → link → runtime →…
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
doca-dpa-hl-tracer
Use this skill when the user runs docadpahltracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm primitive calls, RDMA WR submission, completion drain) — picking TRACE vs CRIT, tuning the JSON config (file-size limits + filesizelimitpolicy, thread…