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 agentmods add instructions/ngvoicu/specmint-core/agents-mdgit clone --depth 1 https://github.com/ngvoicu/specmint-coreWrote 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/instructions/ngvoicu/specmint-core/agents-md)<a href="https://agentmods.dev/instructions/ngvoicu/specmint-core/agents-md"><img src="https://agentmods.dev/badge/instructions/ngvoicu/specmint-core/agents-md.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 | $0.00650 | $0.00650 |
| Opus 5 | $0.00325 | $0.00325 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
specmint-core AGENTS.md 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 5d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
For architectural context across the Mint family (core vs TDD, distribution, evals), read and write to the ngvoicu-sme brain through kluris — /kluris-ngvoicu-sme (Claude Code skill: search, learn, remember, create) or kluris search "<query>" --brain ngvoicu-sme (CLI). Never edit brain files by hand.
Project Structure & Module Organization
SKILL.md: universal, cross-tool skill instructions (Claude Code, Codex, Cursor, Windsurf, Cline, Gemini CLI) — the full forge/implement/resume workflow.references/researcher.md: deep-research subagent brief, spawned via the Task tool during forge.references/spec-format.md: canonicalSPEC.mdformat and markers.references/command-contracts.md: behavioral contract checklist for the skill.skills/specmint-core/SKILL.md: symlink to../../SKILL.mdfor skills-CLI discovery (never replace with a real file)..specs/: local dogfooding output for specs (gitignored in this repo).
Build, Test, and Development Commands
rg --files: fast inventory of repository files before editing.sed -n '1,160p' SKILL.md: inspect skill content in terminal.npx skills add ngvoicu/specmint-core -g -a codex: smoke-test skill installation flow.git log --oneline -n 10: review recent commit style before committing.
This repository has no compile/build pipeline; Markdown and JSON are consumed directly by host tools.
Coding Style & Naming Conventions
- Keep content ASCII Markdown/JSON with concise, imperative instructions.
- Use lowercase, hyphenated filenames for reference docs (for example
references/spec-format.md). - Keep workflow docs procedural (numbered steps, explicit file paths, deterministic behavior).
- Follow spec naming in examples: spec IDs are lowercase-hyphenated (
user-auth-system), task codes are[AUTH-01], and phase markers use[pending],[in-progress],[completed],[blocked].
Testing Guidelines
- No automated test suite currently exists in this repository.
- Perform manual validation for each change:
- Confirm referenced paths/files exist.
- Smoke-test the install/use flow in a disposable project when skill behavior changes (e.g.
npx skills add ./. -g -a claude-code, or copySKILL.mdinto the tool's skills directory, then exercise forge / resume / implement).
- If you change spec-format rules, update both
SKILL.mdandreferences/spec-format.mdin the same PR.
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.
- 5d ago First seen · 38 lines · 650 tokens per session scan A 97be8d5a37f0
specmint-core AGENTS.md is an instructions file published in the GitHub repository ngvoicu/specmint-core (12 stars, last pushed 2mo ago), licensed MIT. It adds 650 tokens to every session, about $0.0032 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 instructions, from other repositories
stockbit-mcp CLAUDE.md
Claude Code instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
curie CLAUDE.md
Claude Code instructions for curie-eng/curie, covering one entry point: curie, release train selection and architecture decision records (adrs).
embedded-systems-architect AGENTS.md
Instructions for Zachariah9420/embedded-systems-architect: This repository ships an agent skill for embedded-systems and edge-AI development work.
catalyst AGENTS.md
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.
gambit CLAUDE.md
Instructions for felipecabargas/gambit, covering gambit, available skills, core, discovery and communication.
claude-skills-by-karpathy CLAUDE.md
Claude Code instructions for ishandutta2007/claude-skills-by-karpathy, covering karpathy-inspired claude skills, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.