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 igapyon/igapyon-agent-skills --skill igapyon-miku-soft-developergit clone --depth 1 https://github.com/igapyon/igapyon-agent-skillsWrote 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/igapyon/igapyon-agent-skills/igapyon-miku-soft-developer)<a href="https://agentmods.dev/skills/igapyon/igapyon-agent-skills/igapyon-miku-soft-developer"><img src="https://agentmods.dev/badge/skills/igapyon/igapyon-agent-skills/igapyon-miku-soft-developer/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/igapyon/igapyon-agent-skills/igapyon-miku-soft-developer"><img src="https://agentmods.dev/badge/skills/igapyon/igapyon-agent-skills/igapyon-miku-soft-developer.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 | $0.00127 | $0.00856 |
| Opus 5 | $0.00063 | $0.00428 |
| Sonnet 5 | $0.00025 | $0.00171 |
| Haiku 4.5 | $0.00013 | $0.00086 |
Grade A, and why
igapyon-miku-soft-developer 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
igapyon-miku-soft-developer
This skill supports explicit miku-soft project creation and maintenance workflows.
Use it only after the user explicitly asks to use igapyon-miku-soft-developer or explicitly asks to apply the miku-soft developer skill. For activation details and the non-activation reply, see references/activation-policy.md.
Modes
After the skill is explicitly active, choose one mode:
- Concept and naming mode: clarify the app concept and decide the miku-soft base repository name before creating files.
- New project mode: create a new miku-soft project or initialize a repository as a miku-soft project.
- Maintenance mode: inspect, update, or repair an existing miku-soft project.
If the mode is unclear after explicit activation, ask a brief clarification before editing.
Core Workflow
Prerequisite: use igapyon-repo-conventions as the repository-conventions baseline for every workflow.
- Read references/activation-policy.md if activation behavior is relevant.
- Read references/architecture-rules.md.
- For concept and naming work, read references/00-concept-naming-workflow.md.
- For new project work, read references/new-project-workflow.md.
- For existing project work, read references/maintenance-workflow.md.
- Read the specific workflow reference when relevant: references/10-node-app-workflow.md, references/11-web-app-workflow.md, references/30-java-straight-conversion-workflow.md, references/31-java-maven-plugin-separation-workflow.md, references/32-node-web-separation-workflow.md, references/40-agent-skills-workflow.md, or references/50-mcp-workflow.md.
- Read references/repo-operations.md for miku-soft-specific additions.
- Inspect the target repository before editing.
- Preserve unrelated user changes.
- Keep product behavior in the product core or upstream runtime artifacts, not in the skill instructions.
What ships with it
60 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.
- assets/agent-skills/.github/workflows/ci.yml 586 B
- assets/agent-skills/.github/workflows/release-build.yml 3.5 KB
- assets/agent-skills/package.json 378 B
- assets/agent-skills/scripts/build-skill-bundle-zip.mjs 987 B runs code
- assets/agent-skills/scripts/build-skill-bundle.mjs 1.6 KB runs code
- assets/agent-skills/templates/skill/agents/openai.yaml 175 B
- assets/agent-skills/templates/skill/assets/.gitkeep 1 B
- assets/agent-skills/templates/skill/lib/.gitkeep 1 B
- assets/agent-skills/templates/skill/references/INDEX.md 283 B
- assets/agent-skills/templates/skill/runtime/.gitkeep 1 B
- assets/agent-skills/templates/skill/SKILL.md.template 1.7 KB
- assets/agent-skills/tests/isolated-bundle-smoke.test.mjs 1.5 KB runs code
- assets/agent-skills/tests/release-bundle-contents.test.mjs 1.6 KB runs code
- assets/java-straight-conversion/.github/workflows/release-cli-runtime.yml 2.5 KB
- assets/java-straight-conversion/.mvn/jvm.config 69 B
- assets/java-straight-conversion/pom-cli-runtime.xml 4.6 KB
- assets/java-straight-conversion/src/assembly/dist.xml 1.4 KB
- assets/node-main-app/.github/workflows/release-cli-runtime-bundles.yml 2.7 KB
- assets/web-app/.github/workflows/release-web-assets.yml 882 B
- assets/web-app/.gitignore 16 B
- assets/web-app/package.json 282 B
- assets/web-app/scripts/stage-web-release-assets.mjs 2.7 KB runs code
- docs/maintenance/2026-07-31-reference-actions-audit/decision-and-roadmap.md 6.2 KB
- docs/maintenance/2026-07-31-reference-actions-audit/github-actions-profile-plan.md 7.3 KB
- docs/maintenance/2026-07-31-reference-actions-audit/implementation-backlog.md 7.3 KB
- docs/maintenance/2026-07-31-reference-actions-audit/numbering-and-structure-plan.md 5.0 KB
- docs/maintenance/2026-07-31-reference-actions-audit/README.md 4.0 KB
- docs/maintenance/adoption-workflow.md 9.3 KB
- docs/maintenance/README.md 3.1 KB
- index.json 13 KB
- references/00-concept-naming-workflow.md 3.9 KB
- references/10-node-app-workflow.md 18 KB
- references/11-web-app-workflow.md 11 KB
- references/30-java-straight-conversion-workflow.md 19 KB
- references/31-java-maven-plugin-separation-workflow.md 17 KB
- references/32-node-web-separation-workflow.md 24 KB
- references/40-agent-skills-workflow.md 15 KB
- references/50-mcp-workflow.md 2.3 KB
- references/activation-policy.md 1.2 KB
- references/architecture-rules.md 5.2 KB
- references/existing-miku-soft-repositories.md 7.7 KB
- references/maintenance-workflow.md 3.6 KB
- references/miku-soft-ai-era-cli-interface.md 12 KB
- references/miku-soft-ai-era-markdown-front-matter.md 9.3 KB
- references/miku-soft-basic/miku-soft-00-overview-design.md 16 KB
- references/miku-soft-basic/miku-soft-10-mainapp-design.md 64 KB
- references/miku-soft-basic/miku-soft-11-web-design.md 22 KB
- references/miku-soft-basic/miku-soft-20-javaapp-design.md 44 KB
- references/miku-soft-basic/miku-soft-21-java-maven-design.md 21 KB
- references/miku-soft-basic/miku-soft-30-straight-conversion.md 58 KB
- references/miku-soft-basic/miku-soft-40-agentskills-design.md 55 KB
- references/miku-soft-basic/miku-soft-50-mcp-design.md 41 KB
- references/new-project-workflow.md 4.8 KB
- references/repo-operations.md 2.0 KB
- references/review/agent-skills.md 6.0 KB
- references/review/mcp-server.md 6.4 KB
- references/review/node-cli.md 17 KB
- references/review/README.md 4.7 KB
- references/review/release-automation.md 8.1 KB
- references/review/single-file-web-app.md 15 KB
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 · 56 lines · 127 tokens per session scan A 1fb13d79d796
igapyon-miku-soft-developer is a skill published in the GitHub repository igapyon/igapyon-agent-skills (2 stars, last pushed 24d ago), licensed Apache-2.0. It adds 127 tokens to every session and 856 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
release-version
Steps to cut a VNote version release (e.g. v4.3.0) — bump the version with scripts/updateversion.py, refresh and fill zhCN/ja translations via lupdate, write the changes.md changelog, and trigger the CI [Release] build. Use when asked to "release", "cut a release", "bump the version", or "prepare vX.Y.Z".
clarity
Draft, rewrite, or review reader-facing prose so it is specific, useful, and recognizably the author's without inventing facts or performing humanness. Use for essays, articles, newsletters, documentation, talks, launch copy, and other important prose that feels generic, hollow, or AI-shaped. Supports co-write…
novel-creator
A Chinese-language writing workflow for creating, continuing, reviewing, polishing, and saving novel chapters.
novel-reviewer
A review and editing workflow for existing novel chapters. It checks story logic, timelines, character states, unresolved clues, world rules, and writing style.
dialoguequality
A dialogue-review system for novels that studies how characters speak and whether their voices remain distinct. It can examine speech habits, sentence length, question frequency, and repeated phrases.
foreshadowing-system
A system for tracking foreshadowing in novels. Foreshadowing means placing a clue or unresolved question earlier in a story and addressing it later.