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/jonathan-vella/apex-accelerator/no-hardcoded-countsgit clone --depth 1 https://github.com/jonathan-vella/apex-acceleratorWrote 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/jonathan-vella/apex-accelerator/no-hardcoded-counts)<a href="https://agentmods.dev/instructions/jonathan-vella/apex-accelerator/no-hardcoded-counts"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/no-hardcoded-counts.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 | $0.00487 | $0.00487 |
| Opus 5 | $0.00244 | $0.00244 |
| Sonnet 5 | $0.00097 | $0.00097 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
apex-accelerator no-hardcoded-counts.instructions.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 4d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No Hard-Coded Counts
Hard-coded numeric counts for project entities drift silently and create maintenance nightmares. This instruction eliminates that class of bug.
Rule
NEVER hard-code counts of agents, subagents, skills, instructions, validators, workflow steps, VS Code extensions, or MCP tools in prose, tables, or comments.
What to Do Instead
Use descriptive language that stays true regardless of count changes:
| Instead of | Write |
|---|---|
| "16 top-level agents and 11 subagents" | "a set of specialized agents and subagents" |
| "38 GA skills" | "the full skill catalog" |
| "25 instruction files" | "instruction files with glob-based auto-application" |
| "7-step workflow" or "8-step workflow" | "the multi-step workflow" |
| "27 validators" | "the validation suite" |
| "13 pricing tools" | "a suite of pricing query tools" |
| "26 pre-installed extensions" | "pre-installed VS Code extensions" |
When Exact Counts ARE Needed
Reference tools/registry/count-manifest.json as the single source of truth. Validators
auto-compute actual values from filesystem globs defined in that file.
Files allowed to contain counts (the allowlist):
tools/registry/count-manifest.json— the manifest itselfCHANGELOG.md— historical entries describe what changed at a point in timeQUALITY_SCORE.mdChange Log column — historical records of state changes- Validator script output — computed dynamically, not hard-coded
Workflow Steps
The workflow includes Step 3.5 (Governance) which makes "7 steps" and "8 steps" both technically correct depending on counting method. To eliminate this ambiguity: always say "multi-step workflow" — never count steps.
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.
- 4d ago First seen · 47 lines · 487 tokens per session scan A 66d494458f71
apex-accelerator no-hardcoded-counts.instructions.md is an instructions file published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed 3d ago), licensed MIT. It adds 487 tokens to every session, about $0.0024 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
squad squad-routing-guard.instructions.md
Squad routing guard — explicit routing rules so the Copilot CLI routes tasks to the right Squad agent instead of handling them directly.
vscode-unify-chat-provider AGENTS.md
Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…
PlatformPlatform AGENTS.md
Instructions for platformplatform/PlatformPlatform, covering behavioral guidelines, build, test, and format, product management tool, auto memory and source of truth.
copilot-instructions copilot-instructions.md
Instructions for SebastienDegodez/copilot-instructions, covering copilot instructions, language policy, development code generation and workflow implementation.
github-copilot-rules testing-xunit.instructions.md
This file provides guidelines for writing effective, maintainable tests using xUnit and related tools.
github-copilot-rules git-message.instructions.md
This file contains the instructions for the commit message format.