Init
asgeirtj/system_prompts_leaks
Initialize new CLAUDE.md file(s) and optional skills/hooks with codebase documentation
A skill your agent uses when the user says 'new project', 'project init', 'what tier', 'scope', or discusses project maturity, complexity budget, or what's appropriate to build.
MITAuto-check passed
Install Governor
$ npx skills add cwinvestments/memstack --skill governor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cwinvestments/memstack governor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cwinvestments/memstack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/governor .claude/skills/governor && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "governor" agent skill from https://github.com/cwinvestments/memstack/tree/master/skills/governor into .claude/skills/governor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "governor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cwinvestments/memstack/tree/master/skills/governorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cwinvestments/memstack --skill governor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cwinvestments/memstack governor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cwinvestments/memstack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/governor .agents/skills/governor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "governor" agent skill from https://github.com/cwinvestments/memstack/tree/master/skills/governor into .agents/skills/governor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "governor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cwinvestments/memstack --skill governor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cwinvestments/memstack governor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cwinvestments/memstack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/governor .cursor/skills/governor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "governor" agent skill from https://github.com/cwinvestments/memstack/tree/master/skills/governor into .cursor/skills/governor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "governor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cwinvestments/memstack.git --path skills/governor--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cwinvestments/memstack --skill governor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cwinvestments/memstack governor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cwinvestments/memstack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/governor .gemini/skills/governor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "governor" agent skill from https://github.com/cwinvestments/memstack/tree/master/skills/governor into .gemini/skills/governor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "governor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cwinvestments/memstack governorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cwinvestments/memstack --skill governor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cwinvestments/memstack.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/governor .github/skills/governor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "governor" agent skill from https://github.com/cwinvestments/memstack/tree/master/skills/governor into .github/skills/governor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "governor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cwinvestments/memstack --skill governor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cwinvestments/memstack governor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cwinvestments/memstack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/governor .opencode/skills/governor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "governor" agent skill from https://github.com/cwinvestments/memstack/tree/master/skills/governor into .opencode/skills/governor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "governor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
governor- GitHub stars
- 423
- Token cost
- ~1.7k tokens
- SKILL.md length
- 788 words
- Files
- 1
- Skills in repo
- 87
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when the user says 'new project', 'project init', 'what tier', 'scope', or discusses project maturity, complexity budget, or what's appropriate to build.
- Works in 4 steps: Determine Project Tier → Apply Tier Constraints → Report Constraints → …
- The user says new project
- SKILL.md covers Activation, Context Guard, Anti-Rationalization and Protocol, plus 4 more sections
- Calls git
What it does
Governor is an agent skill from cwinvestments/memstack. Use when the user says 'new project', 'project init', 'what tier', 'scope', or discusses project maturity, complexity budget, or what's appropriate to build.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Structured skill framework for Claude Code. 130 skills, persistent memory, TokenStack compression, localhost dashboard with 3-agent runner, real-time streaming, MCP tools. The licence is MIT.
When your agent uses it
- The user says new project
- Discusses project maturity
- Complexity budget
- Whats appropriate to build
Example prompts
- “new project”
- “project init”
- “what tier”
- “/governor”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 00370ce. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Governor loads about 1.7k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 788 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from cwinvestments/memstack at commit 00370ce, republished under its MIT licence (© cwinvestments). 788 words, ~1,674 tokens.
Download SKILL.mdSave it as
.claude/skills/governor/SKILL.md (or your agent's skills folder).- name
- governor
- description
- Use when the user says 'new project', 'project init', 'what tier', 'scope', or discusses project maturity, complexity budget, or what's appropriate to build.
- version
- 1.0.0
🏛️ Governor: Portfolio Governance
Enforce tier-appropriate complexity. Prevent over-engineering the #1 waste of time in AI-assisted development.
Activation
When this skill activates, output:
🏛️ Governor: Checking project tier constraints...
Then execute the protocol below.
Context Guard
| Context | Status | Priority |
|---|---|---|
| User starts a new project ("new project", "init", "scaffold") | ACTIVE: assign tier | P1 |
| User asks "what tier", "what's allowed", "scope check" | ACTIVE, report current tier constraints | P1 |
| User proposes work that exceeds current tier | ACTIVE: flag and advise | P2 |
| User is executing work within tier constraints | DORMANT: don't interrupt | none |
| User explicitly overrides ("I know, do it anyway") | DORMANT: user has authority | none |
Anti-Rationalization
If you're thinking any of these, STOP, you're about to let scope creep happen:
| You're thinking... | Reality |
|---|---|
| "Adding tests is always good practice" | Not for prototypes. Tests for throwaway code waste time. |
| "This needs proper auth" | Single-user tools don't need auth. Add it when there are users. |
| "Let me add CI/CD while I'm at it" | CI/CD for a prototype is gold-plating. Ship first. |
| "Error handling should be comprehensive" | Prototype error handling = crash and log. That's it. |
| "I should add monitoring" | < 10 users? Console.log is your monitoring. |
| "This should be configurable" | Hardcode it. Make it configurable when someone asks. |
Protocol
Step 1: Determine Project Tier
Ask or infer the project tier from context:
| Tier | Description | Effort Allocation |
|---|---|---|
| Prototype | Exploring an idea. May be thrown away. | Minimal: working code only |
| MVP | Validated idea, building for first users. | Moderate: basic quality gates |
| Production | Serving real users, needs reliability. | Full: complete quality stack |
If tier is unclear, default to Prototype and escalate only when evidence suggests otherwise.
Step 2: Apply Tier Constraints
Prototype: Move Fast, Break Things
| Allowed | NOT Allowed |
|---|---|
| Working code that demonstrates the idea | Unit tests |
| Hardcoded config values | CI/CD pipelines |
| Console.log for debugging | Type systems / strict typing |
| Single-file scripts | Monitoring / alerting |
| README with setup instructions | Authentication / authorization |
| Infrastructure-as-code | |
| Rate limiting | |
| Database migrations (use SQLite) |
Prototype rule: If it works in a demo, ship it.
MVP: Prove It Works
| Allowed | NOT Allowed |
|---|---|
| Everything from Prototype, plus: | Integration test suites |
| Basic unit tests (happy path only) | Full CI/CD with staging |
| Simple error handling (try/catch at boundaries) | Monitoring dashboards |
| Environment variables for config | Multi-environment deploys |
| Basic input validation | Performance optimization |
| Simple auth (if multi-user) | Horizontal scaling |
| README + basic API docs | Comprehensive logging |
MVP rule: If the first 10 users can use it reliably, ship it.
Production: Reliability Matters
| Allowed | Required |
|---|---|
| Everything from MVP, plus: | Comprehensive tests (unit + integration) |
| Performance optimization | CI/CD pipeline |
| Monitoring and alerting | Error tracking (Sentry or equivalent) |
| Multi-environment deployment | Input validation at all boundaries |
| Horizontal scaling | Authentication + authorization |
| Database migrations | Logging with structured output |
| Rate limiting | API documentation |
Production rule: If it breaks at 3 AM, someone gets paged.
Step 3: Report Constraints
Output a brief summary:
🏛️ Project: {name}
Tier: {Prototype | MVP | Production}
Allowed: {brief list}
NOT allowed: {brief list of key restrictions}Step 4: Flag Violations
When the user proposes work that exceeds the tier, flag it:
🏛️ Governor, Scope check:
You're proposing {X}, but this is a {Tier} project.
{X} is a {higher tier} concern. Current tier doesn't require it.
Want to proceed anyway, or skip it for now?Always defer to the user if they override. Governor advises, doesn't block.
Show full SKILL.md (304 more words)Show less
Anti-Patterns by Tier
Prototype Anti-Patterns: DON'T DO THIS
- Writing tests for throwaway code: If the prototype proves the idea wrong, those tests are wasted
- Adding auth to single-user tools: You're the only user. Skip it
- Setting up CI/CD: You're not deploying to production.
git pushis your CI - Using TypeScript for a quick script: JavaScript is fine for prototypes
- Adding rate limiting: You have 0 users. Rate limit when you have 10
- Creating database migrations: SQLite + direct schema changes. Migrate when you scale
- Building admin dashboards: Database GUI tool (TablePlus, DBeaver) is your admin panel
- Over-abstracting: 3 similar lines > 1 premature abstraction
- Adding comprehensive error handling: Crash and read the stack trace. That's debugging
- Monitoring and alerting: Console output is your monitoring
MVP Anti-Patterns: DON'T DO THIS
- Integration test suites: Happy-path unit tests are enough at MVP
- Multi-environment deploys: One environment. Dev IS production
- Performance optimization: Make it work, make it right, THEN make it fast. You're at step 2
- Horizontal scaling: Vertical scale (bigger server) until proven insufficient
- Comprehensive logging: Log errors and key events. Not every function call
Production Anti-Patterns: DON'T DO THIS
- Skipping tests to "move faster": You'll move slower when bugs hit production
- Manual deployments: CI/CD exists for a reason. Set it up
- No error tracking: If you can't see errors, you can't fix them
- Ignoring security: Production code faces the internet. Act like it
Inputs
- Project name and context
- Current tier (from user, STATE.md, or project CLAUDE.md)
- Proposed work scope
Outputs
- Tier assignment with constraint summary
- Violation flags when scope exceeds tier
- Anti-pattern warnings
Level History
- Lv.1: Base: 3-tier governance system with phase constraints, anti-patterns list, and scope violation flagging. Inspired by Intellegix portfolio governance. (Origin: MemStack v3.2, Feb 2026)
© cwinvestments, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/governor of cwinvestments/memstack.
Open the folder on GitHubat commit 00370ce
Compare with similar skills
Governor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Governor this skillcwinvestments/memstack | 423 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Initasgeirtj/system_prompts_leaks | 69k | — | ~5.5k | Automated safety check: Pass | CC0-1.0 | |
| Initasgeirtj/system_prompts_leaks | 69k | — | ~602 | Automated safety check: Pass | CC0-1.0 | |
| Initbrycewang-stanford/Auto-Empirical-Research-Skills | 4.6k | — | ~596 | Automated safety check: Notes | Custom licence | |
| Agent Coordinator Swarm Initruvnet/ruflo | 74k | 2 repos | ~997 | Automated safety check: Pass | MIT | |
| Free Tier Strategysickn33/agentic-awesome-skills | 47k | 1 repos | ~3.4k | Automated safety check: Pass | MIT |
Similar skills
Init
asgeirtj/system_prompts_leaks
Initialize a new CLAUDE.md file with codebase documentation. An agent skill from asgeirtj/system_prompts_leaks.
Init
brycewang-stanford/Auto-Empirical-Research-Skills
Fills all [FILL:] placeholders across the template to initialize a new research project.
Agent Coordinator Swarm Init
ruvnet/ruflo
Agent skill for coordinator-swarm-init - invoke with $agent-coordinator-swarm-init
Free Tier Strategy
sickn33/agentic-awesome-skills
Design free tiers that convert to paid without creating resentment or abuse.
Swarm Init
ruvnet/ruflo
Initialize a multi-agent swarm with anti-drift configuration.
More from cwinvestments/memstack
All 87 skills in this repoMemstack SEO Site Audit
cwinvestments/memstack
A skill your agent uses when the user says 'SEO audit', 'site audit', 'check SEO', 'audit my site', 'SEO check', 'technical SEO', or is evaluating a website's search engine optimization health, meta…
Memstack SEO Schema Markup
cwinvestments/memstack
A skill your agent uses when the user says 'add schema', 'schema markup', 'JSON-LD', 'structured data', 'rich results', 'rich snippets', or is adding or fixing schema.org structured data for better…
Compress
cwinvestments/memstack
A skill your agent uses when the user says 'tokenstack', 'compression', 'token savings', 'proxy status', or asks about context window usage.
Diary
cwinvestments/memstack
A skill your agent uses when the user says 'save diary', 'log session', 'wrapping up', or at end of a productive session.
Echo
cwinvestments/memstack
A skill your agent uses when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.
Familiar
cwinvestments/memstack
A skill your agent uses when the user says 'dispatch', 'send familiar', 'split task', or needs work split across parallel CC sessions.
Questions about Governor
What does Governor do?
A skill your agent uses when the user says 'new project', 'project init', 'what tier', 'scope', or discusses project maturity, complexity budget, or what's appropriate to build. Governor is an agent skill from cwinvestments/memstack. Use when the user says 'new project', 'project init', 'what tier', 'scope', or discusses project maturity, complexity budget, or what's appropriate to build.
When should I use Governor?
Governor fits situations like: the user says new project; discusses project maturity; complexity budget; whats appropriate to build.
How do I install Governor in Claude Code?
Run `npx skills add cwinvestments/memstack --skill governor -a claude-code`. Or copy the skill folder (skills/governor in cwinvestments/memstack) into .claude/skills/governor in your project. Claude Code loads it when a task matches its description.
How do I install Governor in Codex?
Run `npx skills add cwinvestments/memstack --skill governor -a codex`. Or copy the skill folder (skills/governor in cwinvestments/memstack) into .agents/skills/governor in your project. Codex loads it when a task matches its description.
Can I use Governor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cwinvestments/memstack --skill governor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/governor, .gemini/skills/governor, .github/skills/governor and .opencode/skills/governor in your project.
What does Governor need to run?
Going by SKILL.md and its folder, Governor needs the command-line tools its instructions call (git).
Does Governor access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Governor safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Governor use?
Governor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Governor use?
About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Governor?
Skills that share tags, products or a category with Governor: Init (asgeirtj/system_prompts_leaks, 69k stars), Init (asgeirtj/system_prompts_leaks, 69k stars), Init (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars) and Agent Coordinator Swarm Init (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Governor?
cwinvestments (a GitHub user) maintains it in cwinvestments/memstack, which has 423 GitHub stars. The repository holds 87 skills in this directory. The repository was last updated on September 26, 2026.
Source: cwinvestments/memstack on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.