Mycodo Autonomous Mushroom Control
Let your Muse run the grow tent: sensors, fans and humidifiers on autopilot
- What
- Let your Muse run the grow tent: sensors, fans and humidifiers on autopilot
- Cost
- Free
- Needs
- a Raspberry Pi running Mycodo with InfluxDB 2.x, an SHT45 sensor (temperature/humidity) and an SCD41 sensor (CO2), a relay-controlled fan and a relay-controlled humidifier, Python 3.9+ with PyYAML, and the Hermes agent framework with cron scheduling. You must create the credential file ~/.mycodo/sensor-creds.env yourself (Mycodo API key, InfluxDB token, Pi host address) — never paste credentials into chat, store them in the secure vault and write the file locally yourself.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — turns your Muse into the operator of a mushroom grow tent: a phase-aware decision engine reads temperature, humidity and CO2 sensors via Mycodo on a Raspberry Pi, evaluates readings against species-specific YAML thresholds (lion's mane, oyster, shiitake, reishi, turkey tail, maitake), and fires fan and humidifier relays through colonization, primordia, fruiting and rest phases — with safety guards against oversaturation, a 10-minute follow-up checker that verifies actuator effects, operator overrides, and HTML reports with camera snapshots. Discovered via skills.sh, listed here with credit to its creator by @setasoma. Honest caveats: serious hardware is required (Raspberry Pi running Mycodo + InfluxDB, SHT45 and SCD41 sensors, relay-controlled fan and humidifier, Hermes agent framework with cron); the skill's own documentation records production incidents (a dry-run that silently fired nothing for days, humidity climbing to 99.91% unchecked) — review the safety guards carefully before letting it touch real relays; the contamination-check feature is dormant (standby, no model configured); 1 install on the catalog, but popularity is not a review. Skill Harbor never reviews the code, review it yourself before use. Not verified.
Version:
Quick answer
Mycodo Autonomous Mushroom Control is a free Muse skill that turns your Muse into the operator of a mushroom grow tent. A phase-aware decision engine reads temperature, humidity, and CO2 sensors through Mycodo on a Raspberry Pi, evaluates readings against species-specific thresholds, and fires fan and humidifier relays through colonization, fruiting, and rest phases, with safety guards and follow-up checks.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 7069cb0Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a Raspberry Pi running Mycodo with InfluxDB 2.x, an SHT45 sensor (temperature/humidity) and an SCD41 sensor (CO2), a relay-controlled fan and a relay-controlled humidifier, Python 3.9+ with PyYAML, and the Hermes agent framework with cron scheduling. You must create the credential file ~/.mycodo/sensor-creds.env yourself (Mycodo API key, InfluxDB token, Pi host address) — never paste credentials into chat, store them in the secure vault and write the file locally yourself. Install "Mycodo Autonomous Mushroom Control" for me. An autonomous environmental control skill for a mushroom grow tent: phase-aware decision engine that reads Mycodo sensors, evaluates species-specific thresholds, fires fan and humidifier relays, verifies actuator effects, and produces HTML status reports with camera snapshots. Repository: https://github.com/setasoma/mycodo-hermes-skill Pinned version: install the code at commit 7069cb0cec6f84116f77ca567fe6d24065db34c8 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file for the mycodo-autonomous-control skill (and its helper files and species YAML configs) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "mycodo-autonomous-control". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. wire the sensors and relays on my Pi, create ~/.mycodo/sensor-creds.env, run a dry-run before enabling --execute in cron). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me. Safety note: always run the decision engine WITHOUT --execute first (dry-run) and confirm the report shows sensible relay decisions before scheduling autonomous --execute runs in cron.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It can create or modify files.
- It works with an API key or a token that you provide.
What the scan found — excerpts from the install prompt
- writes files — Prerequisites: a Raspberry Pi running Mycodo with InfluxDB 2.x, an SHT45 sensor (temperature/humidity) and an · Prérequis : un Raspberry Pi avec Mycodo et InfluxDB 2.x, un capteur SHT45 (température/humidité) et un capteur
- uses API keys or tokens — Prerequisites: a Raspberry Pi running Mycodo with InfluxDB 2.x, an SHT45 sensor (temperature/humidity) and an · Prérequis : un Raspberry Pi avec Mycodo et InfluxDB 2.x, un capteur SHT45 (température/humidité) et un capteur
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 7069cb0 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : writes files · uses API keys or tokens
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.