files.py

A workspace file-management module that represents files and folders as a browsable tree instead of a flat list. It hides names beginning with a dot, such as .git or .cache, from the workspace viewer.

In plain words
What is it for?
Use it to list an agent's workspace, retrieve or preview a file by its relative path, and delete a file or folder from that workspace.
Why use it?
It lets users inspect nested project files and preview, download, or remove individual files and directories. It also keeps hidden tooling files out of the interface.

Agent

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 agents/netmindai-open/narranexus/files.py
Clone the repo
git clone --depth 1 https://github.com/NetMindAI-Open/NarraNexus
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 1,154 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 $0.01154
Opus 5 $0.00000 $0.00577
Sonnet 5 $0.00000 $0.00231
Haiku 4.5 $0.00000 $0.00115

Measured 2d ago against content hash 879d6804001e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

files.py 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.

.mindflow/mirror/backend/routes/agents/files.py.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

2026-05-14 — recursive tree + nested raw / delete (pointer-model rework)

The flat "top-level files only" listing became a recursive directory tree so the workspace viewer (Config → Workspace) can browse the structure the agent actually builds (a typical artifact is a folder of files). Server-side filtering: any directory or file whose name starts with . is hidden — the UI never has to know about .cache, .git, hidden tooling state.

New endpoints:

  • GET /{agent_id}/files/raw?path=… — download / inline-preview a single file. The viewer uses this for the "download" and "preview" actions, and the manual "register as artifact" action targets path directly.
  • DELETE /{agent_id}/files/{path:path} — accepts nested relative paths and works for both files (unlink) and directories (rmtree). The previous flat-only signature is replaced.

Schema changes: FileInfo gained name / path / is_dir / children: Optional[List[FileInfo]]; FileListResponse.files was renamed to tree. Pure shape change (no backward compat — frontend is updated in the same change).

agents/files.py — agent workspace file management

Why it exists

Each (agent_id, user_id) has its own workspace under {base_working_path}/{agent_id}_{user_id}/. The agent reads/writes there via the Claude Agent SDK with cwd=workspace and a workspace-containment guard. This router is the frontend's window into that workspace:

  • list the tree to render the workspace section of the agent config panel,
  • download / preview any single file,
  • upload a file from the user's machine into the workspace root,
  • delete any file or subdirectory.

Together with the manual POST /api/agents/{aid}/artifacts/register endpoint in agents/artifacts.py, this lets a user pick a workspace file and turn it into an artifact tab without going through the LLM at all.

Upstream / Downstream

Upstream:

  • Frontend FileUpload.tsx (workspace section of the config panel).
  • Frontend artifact "register from workspace" modal.

Read the full file on GitHub · 107 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 · 107 lines · 0 tokens per session scan A 879d6804001e

Subscribe to this mod's changes

files.py is an agent published in the GitHub repository NetMindAI-Open/NarraNexus (84 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,154 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 2026-08-30.