PheroPath
A filesystem-based stigmergy communication protocol. Use this to leave invisible "pheromones" (signals) on files to communicate context, risks, or status to other agents or your future self without modifying file content.
Best use case
PheroPath is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
A filesystem-based stigmergy communication protocol. Use this to leave invisible "pheromones" (signals) on files to communicate context, risks, or status to other agents or your future self without modifying file content.
Teams using PheroPath should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/PheroPath/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How PheroPath Compares
| Feature / Agent | PheroPath | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
A filesystem-based stigmergy communication protocol. Use this to leave invisible "pheromones" (signals) on files to communicate context, risks, or status to other agents or your future self without modifying file content.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# PheroPath Agent Skill PheroPath allows you to attach context (DANGER, TODO, SAFE, INSIGHT) to files using Extended Attributes (or a sidecar fallback). ## Usage Guide ### 1. Secrete (Leave a Signal) **Script:** `scripts/secrete.py` **When to use:** - **DANGER**: You found a bug/risk you cannot fix immediately. - **TODO**: You are leaving untidied code or suggestions. - **SAFE**: You verified a module is robust. - **INSIGHT**: You want to explain *why* something is implemented this way. **Bash Examples (Few-Shot):** ```bash # Example 1: Mark a file as dangerous due to a race condition python3 scripts/secrete.py "src/concurrency.py" "DANGER" "Rate limit race condition under high load" --intensity 1.0 # Example 2: Leave a TODO note for refactoring python3 scripts/secrete.py "src/legacy_api.py" "TODO" "Needs migration to v2 API schema" # Example 3: Mark a test file as verified python3 scripts/secrete.py "tests/test_auth.py" "SAFE" "Passed all penetration tests" # Example 4: Add architectural insight python3 scripts/secrete.py "src/core/engine.py" "INSIGHT" "Core loop logic derived from paper X" --ttl 168 ``` ### 2. Sniff (Read Signals) **Script:** `scripts/sniff.py` **When to use:** - **ALWAYS** before starting a task in an unfamiliar directory. - Before modifying critical files to check for `DANGER`. **Bash Examples (Few-Shot):** ```bash # Example 1: Sniff a specific file python3 scripts/sniff.py "src/main.py" # Example 2: Sniff an entire directory (recursive) to gather context python3 scripts/sniff.py "src/" --min-intensity 0.1 # Example 3: Parse output (it is JSON) python3 scripts/sniff.py "src/" | jq '.[].message' ``` ### 3. Cleanse (Remove Signals) **Script:** `scripts/cleanse.py` **When to use:** - After fixing a bug (remove `DANGER`). - After completing a task (remove `TODO`). **Bash Examples (Few-Shot):** ```bash # Example 1: Remove signal from a specific file (e.g. after fixing it) python3 scripts/cleanse.py "src/concurrency.py" # Example 2: Prune weak signals (intensity < 0.2) from a directory python3 scripts/cleanse.py "src/" --prune 0.2 # Example 3: Clear ALL signals from a directory (Reset) python3 scripts/cleanse.py "src/" --all ```
Related Skills
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
advanced-skill-creator
Meta-skill that generates domain-specific skills using advanced reasoning techniques. PROACTIVELY activate for: (1) Create/build/make skills, (2) Generate expert panels for any domain, (3) Design evaluation frameworks, (4) Create research workflows, (5) Structure complex multi-step processes, (6) Instantiate templates with parameters. Triggers: "create a skill for", "build evaluation for", "design workflow for", "generate expert panel for", "how should I approach [complex task]", "create skill", "new skill for", "skill template", "generate skill"