material-workbench AGENTS.md

Repository instructions for a Windows desktop catalogue that organizes local media and related information. They define how the program handles files, user data, temporary test libraries, and risky physical changes.

In plain words
What is it for?
Use them when adding media intake, editing metadata, moving or copying files, working with Adobe-related APIs, or testing library operations.
Why use it?
They help prevent accidental overwrites, moves, deletions, unsafe tests, and changes that cannot be rolled back.

Instructions file for CodexOpenCode

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 instructions/mirror4869/material-workbench/agents-md
Clone the repo
git clone --depth 1 https://github.com/mirror4869/material-workbench

Made for: Codex, OpenCode.

Per session 1,140 This file is loaded in full into every session.
When invoked 1,140 The same file — it is already loaded in full.
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 $0.01140 $0.01140
Opus 5 $0.00570 $0.00570
Sonnet 5 $0.00228 $0.00228
Haiku 4.5 $0.00114 $0.00114

Measured 2d ago against content hash 627af2c07e78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

material-workbench 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 2d 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project scope

Material Workbench is a Windows local-first media catalogue. Source code and static assets live in this repository; real media, user metadata, generated indexes, thumbnails, journals, logs, and local configuration do not.

Safety rules

  1. Never use a real media library in tests. Use temporary directories and synthetic fixtures.
  2. Never commit or directly edit user_data.json or runtime journals.
  3. Existing library files must not be silently moved, renamed, overwritten, or deleted.
  4. Desktop intake defaults to a no-overwrite library copy. Moving the original is an explicit warned choice; a copy does not silently relink an external project or make its Desktop source safe to delete.
  5. Destructive or transactional physical changes require preview, explicit confirmation, authoritative server-side revalidation, persistent recovery evidence, and rollback. First-ingest copy instead keeps the source, publishes atomically without overwrite, and removes only its own failed target.
  6. Destructive and Adobe write APIs accept opaque IDs, not browser-provided filesystem paths.
  7. Do not weaken reparse-point, hard-link, stale-plan, project-identity, or concurrent-write guards to make a test pass.
  8. Adobe integration is optional and must fail closed when the external bridge or same-project runtime guard is unavailable.
  9. Keep all text files UTF-8 and preserve stable asset ID algorithms.
  10. Core workflows must remain usable without AI. Agent output is advisory and cannot bypass user confirmation, server-side validation, or recovery gates.
  11. Browse and Organize are presentations of one library. New item actions and query concepts should share a command/query contract instead of creating a capability that exists in only one presentation.
  12. Premiere, Blender, DaVinci Resolve, CapCut/Jianying, and other creative applications are optional capability-declared connectors. Keep reveal and copy-path usable without a connector, and never simulate a host write with UI automation or expose an action whose runtime guard is unavailable.
  13. Keep assets/js/workbench-query.js pure and explicitly driven by item, query, and context inputs. The browser uses catalogue → query → bootstrap → oracle → main order; Organize/Material is the only migrated query adapter. Keep Browse/Home on its legacy implementation until independent equivalence tests pass, and do not imply that both interfaces already share all semantics.
  14. /api/bootstrap/status must remain read-only: it may diagnose but must not scan, repair, install, or write. assets/js/workbench-bootstrap.js may synthesize an empty payload only for a source explicitly reported as missing; invalid or unreadable data blocks loading. Optional dependency failures must gate only the capabilities that require them, and every gated action must also fail closed inside its function body.
  15. Keep inspiration_cards_core.py independent of the HTTP server. Inspiration registry v1 reads are zero-write; an explicit first v2 write requires its dedicated verified backup and one atomic save with one overall revision increment. V2 cards allow 0 to 6 ordered references, at most one cover in the first position, server-derived labels for local IDs, and URLs that the server records without fetching. Migration must inspect every local media/document reference in both schema versions, and exact deduplication must inspect every local asset reference.
  16. The visible inspiration editor supports 0 to 6 ordered references. Keep v1 reads and text-only edits zero-upgrade; send an explicit v2 request only after a real add, remove, reorder, or cover change. Local media and documents must come from the catalogue picker, never from a browser-provided ID or path. If the backend does not explicitly advertise multi_ref_v2, every rich-reference mutation and v2 save must fail closed while compatible v1 text editing remains available.
  17. Ordinary Recycle Bin deletion must check every matching v1/v2 local card reference and confirm it against the current inspiration-registry revision. Keep that confirmation independent from Adobe dependency confirmation; a drift in either revision performs no file move or metadata write. After a confirmed deletion, preserve the card and stored reference and resolve the source as missing.
  18. Keep Daily Oracle local, optional, and non-authoritative. It may open only after an explicit user click and must never be restored as an open dialog by session recovery. The selected deck and normally browser-random salt belong only in localStorage; a fixed non-identifying fallback is allowed when random generation or storage is unavailable. None of these values may enter user_data.json, an index, or a server API. A draw stays stable for the user's local calendar day. Present the bundled traditional and original decks as entertainment and self-reflection, never as medical, legal, financial, safety, or other professional advice. Traditional content may use public-domain Major Arcana symbolism, but must not copy a modern deck's art, text, brand, or interactive assets.

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 1,140 tokens per session scan A 627af2c07e78

Subscribe to this mod's changes

material-workbench AGENTS.md is an instructions file published in the GitHub repository mirror4869/material-workbench (99 stars, last pushed 17d ago), licensed Apache-2.0. It adds 1,140 tokens to every session, about $0.0057 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.