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 Unique-Divine/jiyuu --skill drill-specgit clone --depth 1 https://github.com/Unique-Divine/jiyuuWrote 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/unique-divine/jiyuu/drill-spec)<a href="https://agentmods.dev/skills/unique-divine/jiyuu/drill-spec"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/drill-spec.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 | $0.00081 | $0.00549 |
| Opus 5 | $0.00041 | $0.00275 |
| Sonnet 5 | $0.00016 | $0.00110 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
drill-spec 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
Interview me about a plan, spec, or design until we reach shared understanding. Ask direct questions that resolve concrete decisions, ambiguities, risks, and edge cases. For each question, provide your recommended answer.
-
Ask up to five questions per turn. Ask fewer when a single answer blocks the next useful question. Ask in the chat, not with the question tool.
-
If a question can be answered by exploring the codebase, explore the codebase instead.
-
Record decisions as the discussion progresses. If the user is working from an existing spec, plan, issue, or design document, write resolved answers back into that document iteratively. If there is no obvious document, create or propose a short notes/spec file.
-
When recording implementation decisions, add or update one or more top-level
## Implsections. Use concise logical flows where they make the design easier to execute:input or trigger -> state read/write -> validation -> result -
When recording an answer, capture the decision, rationale, relevant codebase or operational context, and important caveats. Use open checkbox sub-bullets only for unresolved work, decisions, or tests. A resolved decision may remain as a completed decision task or become settled prose, following agent skill
md-tasks. -
Continue drilling while material design ambiguity remains for the implementation sequence being handed off. Answered questions alone do not make that scope ready for implementation. When the design stabilizes:
- Follow agent skill
md-tasksfor a final normalization pass. - Preserve settled decisions and rationale while deriving separate open implementation, validation, rollout, or deferred tasks.
- Check that no actionable consequence remains hidden in narrative prose.
- If the artifact is an epic, follow agent skill
epicsfor placement, structure, and handoff synthesis, including multiple top-level## Implsections when they help separate implementation sequences. - Explicitly defer non-blocking questions so one stable
## Implsequence can proceed without implying that every later sequence is fully specified.
- Follow agent skill
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 · 50 lines · 81 tokens per session scan A 7a341436ac72
drill-spec is a skill published in the GitHub repository Unique-Divine/jiyuu (6 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 549 once invoked, about $0.0004 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
migrate-goldmark-extension-v1-to-v2
Migrate goldmark extension from goldmark v1 to v2.
migrate-goldmark-app-v1-to-v2
Migrate your application from goldmark v1 to v2.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
jwx-guide-v4
Guide for developing Go applications with github.com/lestrrat-go/jwx v4 — parse/sign JWTs, work with JWS/JWE/JWK, pick algorithms, and avoid the common footguns. For developers using jwx, not for developing the library itself.
readme-generate
A tool that analyzes source code to generate English and Chinese README files and related project documentation.
gograph
Go repository intelligence for Claude Code. Use when reading, navigating, editing, reviewing, or refactoring a Go codebase. Exposes 64 query, analysis, and workflow capabilities through the local gograph MCP server, including bounded first-call exploration, AST-aware call graphs, blast-radius analysis, impact, and…