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 EliasOulkadi/shokunin --skill researchgit clone --depth 1 https://github.com/EliasOulkadi/shokuninWrote 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/eliasoulkadi/shokunin/research)<a href="https://agentmods.dev/skills/eliasoulkadi/shokunin/research"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/research/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/eliasoulkadi/shokunin/research"><img src="https://agentmods.dev/badge/skills/eliasoulkadi/shokunin/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 225 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00058 | $0.03053 |
| Opus 5 | $0.00029 | $0.01527 |
| Sonnet 5 | $0.00012 | $0.00611 |
| Haiku 4.5 | $0.00006 | $0.00305 |
Grade A, and why
research 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 12d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
research · 調査
調査 · ちょうさ — "investigation". Source verification and fact-checking for document generation.
Pre-loads facts before writing. Runs BEFORE humanize + kami + kagen in the document pipeline. Prevents hallucinated data, fake citations, unverified claims.
Based on: CIA Structured Analytic Techniques (Heuer & Pherson), US Government Tradecraft Primer, NPR Training verification guide, Princeton triangulation methodology, OSINT verification tiers (War Intel Hub), journalistic cross-verification research (Godler & Reich), AI hallucination benchmarks (Vectara HHEM 2026), and evidence hierarchy frameworks (NHMRC).
Core principle
Sources before phrasing. Do not write a claim without verifying it first. Every number, date, name, version, and citation must be traced to a primary or reputable secondary source.
Evidence hierarchy (adapted from NHMRC + intelligence community)
Use this hierarchy to determine the weight of each source:
| Level | Type | Example |
|---|---|---|
| 1 — Direct primary | Official document, direct capture, observed data | Real HTTP response, source code, DB dump, screenshot |
| 2 — Official primary | Official statement, public documentation, filing | SEC filing, CVE entry, official changelog, press release |
| 3 — Reputable secondary | Established outlet, peer-reviewed paper, curated database | NVD, Wordfence, OWASP, Reuters, arXiv |
| 4 — Multiple independent sources | 3+ unrelated sources report the same | Cross-reference across tech blogs + forums + docs |
| 5 — Single source with evidence | One verifiable source but no corroboration | Researcher blog with reproducible evidence |
| 6 — Unverified | Unsupported claim, rumor, speculation | Do NOT use as fact in a document |
Rule: a professional document only uses levels 1–4 for factual claims. Level 5 for context or direct quotes, marked as such. Level 6 is not published.
Source verification protocol (NPR + Princeton triangulation)
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.
- 12d ago First seen · 240 lines · 58 tokens per session scan A de70e9780f45
research is a skill published in the GitHub repository EliasOulkadi/shokunin (113 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 3,053 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
python-docs
Create, update, and sync Python project documentation from source code. Use when asked to document a module, generate API references, create architecture diagrams with Mermaid, update docs after code changes, or keep documentation in sync with source. Triggers include "document", "write docs", "update docs", "sync…
code-refactor
Refactor Python code to match this repo's coding standards and style. Use when the user asks to "refactor", "clean up", "fix coding standards", or "apply best practices" to a module, file, or directory in this repo. Applies python-best-practices, pydantic v2, pytorch-lightning, and python-docs conventions as relevant…
quality
PALADIN quality gatekeeper. Two-stage system: Stage 1 checks spec compliance (pass/fail, blocks everything on failure). Stage 2 scores project health 0-100 across 6 tiers. Issues verdict: SHIP IT / SHIP WITH CAUTION / NOT READY / BLOCKED. Evidence Before Claims: every finding must cite the file, line, and what was…
refresh
Use when an existing contextualizer's references may have drifted from current upstream state — typically weekly, or whenever a few days of upstream changes have accumulated — to bring them back into agreement.
apply
Use when a staged proposal has been reviewed and signed off — REVIEW.md Step 3 ticked reviewed or provisional — and is ready to promote into the live contextualizer.
config-set
Use when changing an engine-wide config value — currently diff.tool, the command /skill-engine:review prints for inspecting a proposed-vs-live diff.