svg-injector: Instructions file for Codex

AGENTS.md

svg-injector AGENTS.md is an instructions file for Codex, OpenCode from tanem/svg-injector. It costs 2,213 tokens per session, scanned A, original, MIT.

Repository-specific instructions for coding agents working on tanem/svg-injector, covering documentation, architecture, writing style, known limits, and SVG sprites.

In plain words
What is it for?
Use them when editing or reviewing that codebase, especially changes involving agent instructions, documentation, architecture, or SVG sprites.
Why use it?
They give an agent the project rules and context needed to make changes that fit the repository.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is tanem/svg-injector's own configuration. It tells Codex and OpenCode how to work on svg-injector itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything svg-injector configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tanem/svg-injector. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tanem/svg-injector/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tanem/svg-injector

Made for: Codex, OpenCode.

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 svg-injector AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tanem/svg-injector/agents-md/github.svg)](https://agentmods.dev/instructions/tanem/svg-injector/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tanem/svg-injector/agents-md"><img src="https://agentmods.dev/badge/instructions/tanem/svg-injector/agents-md/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.

agentmods 80×15 button for svg-injector AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tanem/svg-injector/agents-md"><img src="https://agentmods.dev/badge/instructions/tanem/svg-injector/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,213 This file is loaded in full into every session.
When invoked 2,213 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02213 $0.02213
Opus 5.5 $0.00885 $0.00885
Sonnet 5.5 $0.00443 $0.00443
Haiku 4.5 $0.00221 $0.00221

Measured 1mo ago against content hash 55eec27b43ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

svg-injector 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 1mo 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.

AGENTS.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Rules for coding agents that the code and config don't already state. Keep it that way: a constraint that can live in a comment next to the thing it constrains belongs there, not here.

Writing

  • NZ English everywhere ("colour", "behaviour", "initialise").
  • Commit subjects and PR titles are one plain capitalised sentence, git log --oneline style, with no conventional-commit prefix (feat:, fix:, chore(deps):). Nothing reads a prefix: the version bump comes from the PR label.
  • Add a commit body whenever the change had a reason the diff does not show: what it fixes, what it rules out, what constraint forced the shape it has. Hard-wrap it at 72 columns.
  • PR titles are copied verbatim into the generated release notes, so write them as the changelog line you want readers to see.
  • Do not hard-wrap markdown files, PR descriptions or issue descriptions.
  • README.md follows standard-readme. Per-feature detail belongs in examples/*/README.md, linked from there.
  • README.md states current behaviour; MIGRATION.md states what changed and keeps the upgrade steps in full. Neither re-derives the other.

Architecture

SVGInjector runs one pipeline per element: split the sprite fragment off the URL, load, transform, swap, settle. CONTEXT.md names the stages. inject-element.ts is that pipeline, and the header comments of the modules under it say what each owns.

Every path out of injectElement, errors included, settles exactly once. Add one that doesn't and afterAll silently never fires. The transform and beforeEach run consumer code, and are the two paths where a throw has to settle before it escapes.

XHR is a decision, not leftover legacy. It carries the file:// allowances make-ajax-request.ts documents, and its content-type check runs at readyState 2 so a rejected response aborts before its body arrives. fetch does neither. Don't migrate it without new evidence. Safari is the engine that decides anything file:// and the only one those allowances are load-bearing in; measured on Chrome 151, Safari 26.5 and Firefox 146.

Read the full file on GitHub · 110 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. 1mo ago Changed · -100 lines · -701 tokens per session 55eec27b43ae
  2. 1mo ago Changed · -8 lines · +173 tokens per session b8a2f7291d3b
  3. 1mo ago Changed · +15 lines · +158 tokens per session 19f2c647a969
  4. 2mo ago First seen · 203 lines · 2,583 tokens per session scan A 23bc0568a64b

Subscribe to this mod's changes

svg-injector AGENTS.md is an instructions file published in the GitHub repository tanem/svg-injector (110 stars, last pushed 4d ago), licensed MIT. It adds 2,213 tokens to every session, about $0.0089 per session on Opus 5.5. 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.

Related

svg-injector AGENTS.md compared with instructions from other repositories

svg-injector AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
svg-injector AGENTS.mdtanem/svg-injectorInstructions file1104d agoMITA2,213Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode