Borrowing it
Nothing to install: this file belongs to jonathan-vella/apex-accelerator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jonathan-vella/apex-accelerator/main/.github/instructions/no-heredoc.instructions.mdgit 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-heredoc)<a href="https://agentmods.dev/instructions/jonathan-vella/apex-accelerator/no-heredoc"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/no-heredoc/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/instructions/jonathan-vella/apex-accelerator/no-heredoc"><img src="https://agentmods.dev/badge/instructions/jonathan-vella/apex-accelerator/no-heredoc.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 | $0.00599 | $0.00599 |
| Opus 5.5 | $0.00240 | $0.00240 |
| Sonnet 5.5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
Grade A, and why
apex-accelerator no-heredoc.instructions.md scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
navigation (`ls`, `cd`, `mkdir`, `rm`), and downloads (`curl`, `wget` How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MANDATORY: File Operation Override
[!CAUTION] Agent-authored file content must go through file-editing tools. Interactive terminal transport and quoting have caused corruption in prior runs; this repository policy avoids that pathway. Heredoc/redirection syntax is not inherently corrupting, and committed scripts and normal log capture are not prohibited by this policy.
Rule
Do not use cat, echo, printf, tee, or redirects to author multi-line source or
artifact content from chat. Use available file creation/editing tools instead.
Build tools, formatters, generators, downloads and output/log capture retain their
ordinary behavior within the authorized task.
Allowed Terminal Commands
Package management, builds, tests, git, running scripts, filesystem
navigation (ls, cd, mkdir, rm), and downloads (curl, wget
— not piped to files with content manipulation).
Sub-rule: No heredoc'd code into node -e / python3 -c
Do not transport agent-authored multi-line interpreter code through live heredocs. Unquoted delimiters permit shell expansion before the interpreter receives the code; quoted delimiters change those semantics but do not waive the editing-tool policy.
Expansion hazards with unquoted heredoc delimiters include:
- Backtick template literals (
`${value}`) — interpreted as command substitution. ${variable}— interpreted as parameter expansion.$(command)— interpreted as command substitution.\u0000and other escape sequences the shell touches before passing on.
Forbidden patterns: node -e "<<EOF ... EOF", python3 -c "$(cat <<EOF ... EOF)" and
cat <<EOF | node when the body contains those constructs. Instead, write the script to
tmp/run-once.mjs (or .py) with the file-edit tool and run it, so the editing tool
controls quoting end-to-end.
Sub-rule: No writes to agent-output/** via shell
Never write agent-output/** through heredocs, >/>>, or tee; use file-editing tools.
Read-only inspection (ls, cat, wc -l) is fine. This is the agent-facing
No-Shell-Writes-to-Agent-Output rule,
enforced in committed snippets by the safe-shell agent-output-no-heredoc check
(tools/scripts/safe-shell.mjs); shell writes have silently corrupted JSON sidecars before.
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.
- 6d ago Changed · +1 lines · +2 tokens per session ad17a9208ddd
- 1mo ago Changed · -43 lines · -299 tokens per session 5d98a861da74
- 1mo ago First seen · 94 lines · 896 tokens per session scan A 265c03846e9d
apex-accelerator no-heredoc.instructions.md is an instructions file published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed yesterday), licensed MIT. It adds 599 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.