Borrowing it
Nothing to install: this file belongs to zalom/plastic. 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/zalom/plastic/main/AGENTS.mdgit clone --depth 1 https://github.com/zalom/plasticWrote 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/zalom/plastic/agents-md)<a href="https://agentmods.dev/instructions/zalom/plastic/agents-md"><img src="https://agentmods.dev/badge/instructions/zalom/plastic/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.
<a href="https://agentmods.dev/instructions/zalom/plastic/agents-md"><img src="https://agentmods.dev/badge/instructions/zalom/plastic/agents-md.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 | $0.02340 | $0.02340 |
| Opus 5.5 | $0.00936 | $0.00936 |
| Sonnet 5.5 | $0.00468 | $0.00468 |
| Haiku 4.5 | $0.00234 | $0.00234 |
Grade A, and why
plastic 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 22d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plastic
Intent-driven state management for AI coding sessions.
Broken data: fix it or remove it, never build around it
Wrong data (a blank record, a junk field, a failed fetch or import) is fixed first. When it cannot be fixed, the erroneous records are removed. Never design, code, test, or screenshot around broken data. A legitimately absent value is not broken data. Owner ruling 2026-09-05, global rule.
Stack
- Language: Ruby (scripts), JavaScript/Node.js (npm package, installer)
- Framework: npm package that ships the installer and the
plasticcommand (bin/plastic). The former workflow skills no longer ship;skills/keeps only the shared_decision-tables.md. - Testing: Minitest. See the Testing section below for the correct full-suite command.
- Source: this repository. The source command line runs as
ruby bin/plastic. - Remote: [email protected]:zalom/plastic.git
Defaults
- Release process: commit_and_push, github_release, npm_publish
- Version files: package.json, .claude-plugin/plugin.json, .claude-plugin/marketplace.json
- Tag format: v{{version}}
- All bash scripts must work under macOS /bin/bash 3.2 (no bash 4.x features)
- Bump all 3 version files on every fix/feature release
Searching Plastic's stores
plastic search TERMS is Plastic's own store search index, built on sqlite3, the same
install-time checked dependency as git (see the Stack section above). Search it before
re-deriving an existing decision, spec, or outcome. The stores are the memory.
QMD, Serena, and Enola are companion tools a person can run by hand beside Plastic; see
plastic help tools (docs/help/tools.md) for what each one does and how to reach for it.
Intent 391 (2.0) dissolved every Plastic-owned integration with the three: no Plastic
command, hook, or script starts, registers with, reindexes, or reads from any of them. When
QMD is set up, its own qmd query (structured intent/lex/vec/hyde) or qmd search (BM25,
no model downloads) runs directly against the store files, outside Plastic, the same as it
would against any other directory of markdown.
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.
- 22d ago Changed · -5 lines · -217 tokens per session 8ccca15a989c
- 23d ago Changed · +7 lines · +176 tokens per session 9b531cdd0436
- 24d ago Changed · +11 lines · +240 tokens per session 7d461688aefd
- 1mo ago First seen · 132 lines · 2,141 tokens per session scan A cebba0006993
plastic AGENTS.md is an instructions file published in the GitHub repository zalom/plastic (11 stars, last pushed yesterday), licensed MIT. It adds 2,340 tokens to every session, about $0.0094 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 2026-08-31.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).