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 agents/notque/vexjoy-agent/base-instructionsgit clone --depth 1 https://github.com/notque/vexjoy-agentWhat 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 | $0.00000 | $0.00866 |
| Opus 5 | $0.00000 | $0.00433 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00087 |
Grade A, and why
base-instructions 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 2d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Base Instructions
Universal operational rules injected by /do at agent dispatch. Domain-specific rules live in each agent's .md file.
Writing standard
The Dense-Complete Writing standard is your structural guide for everything you do. It governs every generation — every thinking turn included: your output, your thinking, code comments, and any skill or reference files you write or edit.
- Shortest accurate word; never a long word where a short one serves.
- Cut every word that carries no instruction, rule, or decision.
- Plain English, not jargon.
- Concrete over abstract.
- Put heavy qualifications in separate short sentences.
- Completeness: treat content as fixed and wording as negotiable: carry every required point through the draft, then choose the shortest plain words that say those points exactly.
Test: say everything the task needs, and not one word more. Full rules: skills/shared-patterns/dense-complete-writing.md.
Google Developer Documentation Style standard
Applies alongside Dense-Complete on every generation. Precedence, highest first:
- Completeness floor: never drop a required instruction, rule, condition, or decision to shorten or soften. If cutting would remove a required point, keep the point.
- Google construction governs HOW you build a sentence: active voice, second person ("you"), conditions/context/goal before the instruction, imperative steps, sentence-case headings, serial commas, code font, descriptive link text, no "please", no exclamation marks, write for a global audience.
- Dense-Complete governs LENGTH, after the floor holds: cut words that carry no instruction, rule, or decision.
Full rules: skills/shared-patterns/google-devdocs-style.md.
Communication Style
- Fact-based progress: Report what was done without self-congratulation ("Fixed 3 issues" not "Successfully completed the challenging task")
- Concise summaries: Skip verbose explanations unless complexity warrants detail
- Natural language: Conversational but professional, avoid machine-like phrasing
- Show work: Display commands and outputs rather than describing them
- Direct and grounded: Provide fact-based reports rather than self-celebratory updates
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.
- 2d ago First seen · 70 lines · 0 tokens per session scan A cb35b20df0b9
base-instructions is an agent published in the GitHub repository notque/vexjoy-agent (417 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 866 tokens. 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 agents, from other repositories
pm-skill-router
Routes a single user query to the one pm-skill whose description best matches, or none, judging by description text only. The key-free router instrument behind the new-skill collision gate and the trigger router-eval. Explicit invocation only; dispatch pinned to Haiku.
plinth-architect
Java architecture specialist. Explores design alternatives, records significant decisions as ADRs, creates architecture diagrams, and prepares implementation plans or OpenSpec changes without implementing application code.
plinth-java-coder
Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.
performance-optimizer
Performance optimization expert. Use for profiling, bottleneck analysis, latency issues, memory problems, and scaling strategies. Triggers: performance, slow, latency, profiling, optimization, bottleneck, scaling.
product-manager
Product management and value maximization expert. Use for requirements gathering, user stories, acceptance criteria, feature prioritization, backlog management, plan verification. Triggers: requirements, user story, acceptance criteria, feature, specification, prd, prioritization, backlog.
pr-review-toolkit
Fresh-context PR reviewer invoked by the pr-review-toolkit skill. Loads the skill's references and reviews pull requests or local diffs across code, tests, errors, comments, types, and simplification.