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 ngvoicu/kluris --skill specmint-core-htmlgit clone --depth 1 https://github.com/ngvoicu/klurisWrote 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/ngvoicu/kluris/specmint-core-html)<a href="https://agentmods.dev/skills/ngvoicu/kluris/specmint-core-html"><img src="https://agentmods.dev/badge/skills/ngvoicu/kluris/specmint-core-html/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/ngvoicu/kluris/specmint-core-html"><img src="https://agentmods.dev/badge/skills/ngvoicu/kluris/specmint-core-html.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 | $0.00066 | $0.02868 |
| Opus 5 | $0.00033 | $0.01434 |
| Sonnet 5 | $0.00013 | $0.00574 |
| Haiku 4.5 | $0.00007 | $0.00287 |
Grade A, and why
specmint-core-html 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Mint Core HTML — Kluris Companion
Turn ephemeral plans into structured, persistent specs built through deep
research and iterative interviews. This HTML variant uses .specs/<id>/SPEC.html
as the canonical spec document, not a markdown spec plus a separate view. The
HTML file carries metadata, lifecycle state, diagrams, code previews, mockups,
decision logs, and deviations in one human-openable artifact.
When this file is referenced from a Kluris-generated brain skill, read and
follow it directly from ~/.kluris/companions/specmint-core-html/SKILL.md.
Do not ask the user to install Specmint separately. Kluris vendors companions
as single SKILL.md files, so every rule needed for companion mode is below.
Critical Invariants
- Canonical files
- Registry:
.specs/registry.md(markdown index) - Per-spec document:
.specs/<id>/SPEC.html - Research notes:
.specs/<id>/research-*.md - Interview notes:
.specs/<id>/interview-*.md - Scratch, if needed:
.specs/<id>/artifacts/
- Registry:
- Authority rule: the JSON inside
<script type="application/json" id="spec-meta">is authoritative for identity and spec status.data-statusattributes on phases, tasks, and acceptance criteria are authoritative for progress. - Active-spec rule: target exactly one active spec at a time.
- HTML is the source of truth: do not create or update a parallel markdown spec for an HTML companion spec.
- Progress tracking is sacred: after completing any task, immediately
update
SPEC.html(data-status, phase transitions, updated date) and.specs/registry.md(progress/date). Re-read both files before moving on. - Single-file companion mode: use inline HTML/CSS/JS patterns in the
SPEC.htmlyou write. Do not rely on unavailable sibling template or asset files from a separate plugin install.
Registry Format
Create .specs/registry.md if missing:
# Spec Registry
| ID | Title | Status | Priority | Progress | Updated |
|----|-------|--------|----------|----------|---------|
| user-auth-system | User Auth System | active | high | 0/12 | 2026-05-23 |
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 · 229 lines · 66 tokens per session scan A 65c893150beb
specmint-core-html is a skill published in the GitHub repository ngvoicu/kluris (7 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 2,868 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 2026-08-31.
Other skills, from other repositories
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres
Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations. Trigger when user asks to: Design or modify PostgreSQL tables, schemas, or data models Choose data types, constraints, indexes, or partitioning…
prompt-sensei
Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.
pdlc-feature
An automated workflow for taking a new software feature from a description or requirements document through requirements, design, testing, implementation, review, and release preparation. It keeps one feature ID across the documents and requires tests before implementation.
pdlc-quality
A quality gate that runs configured coverage, end-to-end, and lint checks, compares their real results with declared targets, and creates a report for human approval.
pdlc-adopt
A tool for bringing an existing software project into a documented development process. It scans the project, identifies its services, applications, technologies, databases, and APIs, and can create baseline documents without changing code.