fix-env

fix-env is a skill for Claude Code from evo-design/proto-tools. It costs 202 tokens per session (2,494 once invoked), scanned C, original, MIT.

A guide for repairing a tool's environment when its setup or installation fails.

In plain words
What is it for?
It helps eject a tool's setup into an editable folder, enable detailed setup output, patch setup files, and configure the tool to use the patched copy.
Why use it?
It explains how to diagnose setup errors and apply a fix locally or prepare a fix for the project itself.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is proto-tools eject-standalone <toolkit> # -> ./proto_standalone/<toolkit>/.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 fix-env

README.md
[![agentmods](https://agentmods.dev/badge/skills/evo-design/proto-tools/fix-env.svg)](https://agentmods.dev/skills/evo-design/proto-tools/fix-env)
Your own site
<a href="https://agentmods.dev/skills/evo-design/proto-tools/fix-env"><img src="https://agentmods.dev/badge/skills/evo-design/proto-tools/fix-env.svg" alt="Measured on agentmods" height="20"></a>
Per session 202 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,494 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 5.1 $0.00202 $0.02494
Opus 5 $0.00101 $0.01247
Sonnet 5 $0.00040 $0.00499
Haiku 4.5 $0.00020 $0.00249

Measured 6d ago against content hash 47c215feec38, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

fix-env scanned grade C with 1 finding 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 6d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf tool_envs/{tool}_env
.claude/skills/fix-env/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fix-env

When to use: a tool's environment fails to build or work, and you need to fix it — either just on the current machine, or as a fix the whole project should ship.

Two ways to fix an env

The diagnosis is identical; what differs is where you apply the fix and how compatible it has to be. Decide the mode first; the failure patterns and workflow below apply to both.

Local fix — "I just need this tool working on my machine"

For when you (or a user you're helping) hit a broken env and want it working now, without modifying the installed package. Works for any install, including a non-editable pip install where the packaged files sit in read-only site-packages.

  1. Eject the tool's setup into an editable copy and set the variable it prints:
    proto-tools eject-standalone <toolkit>          # -> ./proto_standalone/<toolkit>/
    export PROTO_<TOOLKIT>_STANDALONE_DIR=$PWD/proto_standalone/<toolkit>
    
  2. See the failure live by re-running the tool with PROTO_ENV_VERBOSE=1 (streams setup.sh output to your terminal); diagnose with the patterns below.
  3. Patch the ejected files (setup.sh, etc.) under ./proto_standalone/<toolkit>/.
  4. Rebuild by re-running the tool — with the variable set, the next call builds from your copy under an isolated env name. Iterate until it runs.

Never edit the installed package. Tell the user to export the variable per project (e.g. a direnv .envrc) so it applies only where they want. Reference: "Overriding a tool's standalone env" in notes/tool-environments.md.

Contributed fix — "the packaged setup should change for everyone"

For when you have the repo (editable install) and the fix belongs upstream so every platform benefits.

You will only be testing on the current machine. Assume the existing setup works on other clusters. Make surgical changes to standalone/setup.sh (and other standalone/ files) that fix the current machine while maintaining compatibility with other platforms, using defensive patterns (|| true, conditional checks, graceful fallbacks), then commit them.

Read the full file on GitHub · 168 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 168 lines · 202 tokens per session scan C 47c215feec38

Subscribe to this mod's changes

fix-env is a skill published in the GitHub repository evo-design/proto-tools (125 stars, last pushed 2d ago), licensed MIT. It adds 202 tokens to every session and 2,494 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

troubleshoot

Diagnose and resolve common issues in spatial transcriptomics analysis. Use when analysis fails, produces unexpected results, or user encounters errors. Triggers: "error", "failed", "not working", "issue", "problem", "help", "unexpected result", "debug", "fix", "wrong output".

cafferychen777/ChatSpatial · 65 tokens

understanding-streamlit-architecture

Explains Streamlit's internal architecture including backend runtime, frontend rendering, and WebSocket communication. Use when debugging cross-layer issues, understanding how features work end-to-end, planning architectural changes, or onboarding to the codebase. Covers ForwardMsg/BackMsg protocol, script rerun…

streamlit/streamlit · 75 tokens

fixing-streamlit-ci

Analyze and fix failed GitHub Actions CI jobs for the current branch/PR. Use when CI checks fail, PR checks show failures, or you need to diagnose lint/type/test errors and verify fixes locally.

streamlit/streamlit · 47 tokens

developing-with-streamlit

Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st.…

streamlit/streamlit · 128 tokens

analyze-ci

Analyze failed GitHub Action jobs. Takes one or more GitHub URLs (job, workflow-run, or PR) and summarizes each failure with root cause and log paths.

mlflow/mlflow · 38 tokens

trulens-instrumentation

Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.

truera/trulens · 25 tokens