instructions

instructions is a command for coding agents from MadaraUchiha-314/the-loop. It costs 0 tokens per session (989 once invoked), scanned A, original, MIT.

A command that checks whether a project's configured instruction documents can be found and read. It resolves each path, shows its status, and explains that later documents override earlier ones when rules conflict.

In plain words
What is it for?
Checking repository or machine-wide instruction paths, reviewing their order and notes, and handling missing files as warnings, errors, or ignored entries.
Why use it?
Projects often depend on custom guidance files, and a missing or incorrectly configured file can silently change how work is done. This command makes those files and their loading status visible.

Command

Part of the the-loop plugin — 2 skills, 37 commands, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add commands/madarauchiha-314/the-loop/instructions
Clone the repo
git clone --depth 1 https://github.com/MadaraUchiha-314/the-loop

Or install the-loop, the plugin that ships this one along with the rest of its 2 skills, 37 commands, 2 hooks.

Wrote 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.

agentmods badge for instructions

README.md
[![agentmods](https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/instructions.svg)](https://agentmods.dev/commands/madarauchiha-314/the-loop/instructions)
Your own site
<a href="https://agentmods.dev/commands/madarauchiha-314/the-loop/instructions"><img src="https://agentmods.dev/badge/commands/madarauchiha-314/the-loop/instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00989
Opus 5 $0.00000 $0.00495
Sonnet 5 $0.00000 $0.00198
Haiku 4.5 $0.00000 $0.00099

Measured 5d ago against content hash 7f110f8a22f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

docs/cli/commands/instructions.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

instructions

Which of the custom instruction docs your project registers actually resolve — so "is the-loop really reading my conventions?" is a question you can answer, and onMissing: error is a setting that errors.

the-loop instructions [--root .] [--format table|markdown|json]

What it reads

customInstructions.docs in the repository's harness config — the ordered list of your own rule and guideline files the loop reads before working an item (instructions reference):

customInstructions:
  docs:                                       # ordered; later docs win on conflict
    - path: docs/team-conventions.md          # repo-relative …
      notes: House TS style, naming, PR etiquette.
    - path: /home/me/company-wide-rules.md    # … or absolute (per-machine)
      notes: Org-wide security & dependency policy.
  onMissing: warn                             # warn | error | ignore

It reports each entry in configured order — order matters, because later docs win on conflict — with its configured path, the absolute path it resolved to, your notes, and its state.

States

State Meaning
present The file is there and readable. Its guidance reaches the agent.
missing Nothing resolves at that path (including a broken symlink). Usually a typo or a moved file.
unreadable Something is there, but it is not a readable text file — a directory, a device node, an unpermitted file, or binary content.
invalid The entry itself is unusable: no path, a blank one, or not a mapping.

missing and unreadable are kept apart on purpose: "your path is wrong" and "your path is right but the target is not a doc" send you to different places.

Exit code

Everything that is not present counts as unresolved — invalid included, because a registration the-loop could not understand is guidance that is not reaching the agent. What happens then is customInstructions.onMissing:

Read the full file on GitHub · 98 lines

Changes

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.

  1. 5d ago First seen · 98 lines · 0 tokens per session scan A 7f110f8a22f4

Subscribe to this mod's changes

instructions is a command published in the GitHub repository MadaraUchiha-314/the-loop (4 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 989 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 2026-08-31.