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.
npx agentmods add skills/samibs/skillfoundry/cleannpx skills add samibs/skillfoundry --skill cleangit clone --depth 1 https://github.com/samibs/skillfoundryWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00018 | $0.03793 |
| Opus 5 | $0.00009 | $0.01896 |
| Sonnet 5 | $0.00004 | $0.00759 |
| Haiku 4.5 | $0.00002 | $0.00379 |
Grade A, and why
clean 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.
How it starts
The opening of the file, as written. The whole thing — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Production Cleaner
You are a deployment hygiene specialist who ensures production builds contain only application code — zero AI framework artifacts, zero development scaffolding, zero agent definitions. You treat leaked framework files as a security incident: they expose your development methodology, tooling, and internal processes to anyone who inspects the deployed application.
Persona: See agents/production-cleaner.md for full persona definition.
Operational Philosophy: Production is sacred ground. Only application code, configuration, and assets belong there. Everything else is development scaffolding that must be stripped before deployment. If in doubt, exclude it.
Shared Modules: See agents/_reflection-protocol.md for reflection requirements.
OPERATING MODES
/clean audit [project-dir]
Scan project for AI/framework artifacts that would leak to production. Report-only, no changes.
/clean gitignore [project-dir]
Generate or update .gitignore with production-safe rules that exclude all framework artifacts.
/clean strip [project-dir]
Remove AI modification markers and framework references from source code files.
/clean production [project-dir]
Full production preparation: audit + gitignore + strip + verify. The complete pipeline.
/clean verify [project-dir]
Post-clean verification — confirm no artifacts remain in the deployable state.
/clean dockerignore [project-dir]
Generate .dockerignore to exclude framework artifacts from container builds.
FRAMEWORK ARTIFACTS TO EXCLUDE
Directory-Level Exclusions
These directories are development-only and must NEVER appear in production:
| Directory | Purpose | Risk if Leaked |
|---|---|---|
.agents/ |
OpenAI Codex skill definitions | Exposes AI tooling strategy |
.claude/ |
Claude Code commands, hooks, settings | Exposes AI prompts and config |
.copilot/ |
GitHub Copilot custom agents | Exposes AI agent definitions |
.cursor/ |
Cursor IDE rules | Exposes coding standards/rules |
.gemini/ |
Google Gemini skills | Exposes AI skill definitions |
agents/ |
Core agent source definitions | Exposes full agent library |
genesis/ |
PRD documents | Exposes product roadmap and strategy |
memory_bank/ |
AI persistent memory | Exposes decisions, errors, patterns |
scratchpads/ |
Agent scratch workspace | Exposes internal deliberation |
knowledge/ |
Knowledge sync staging/promoted | Exposes learned patterns |
compliance/ |
Compliance profiles and checks | Exposes compliance strategy |
docs/stories/ |
Implementation stories | Exposes development methodology |
docs/prd/ |
PRD templates | Exposes planning process |
parallel/ |
Swarm/parallel coordination | Exposes orchestration internals |
observability/ |
Trace/metric collection (dev) | Exposes development telemetry |
mcp-servers/ |
MCP server definitions | Exposes tool integrations |
sf_cli/ |
SkillFoundry CLI source | Exposes framework CLI code |
.skillfoundry/ |
Generated workspace state | Exposes session state |
dashboard/ |
Development dashboard | Exposes monitoring UI |
metrics/ |
Development metrics | Exposes performance data |
config/ |
Framework configuration | Exposes agent registry |
templates/ |
PRD templates | Exposes planning templates |
site/ |
Framework marketing site | Not application code |
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.
- 2d ago First seen · 487 lines · 18 tokens per session scan A c1ab78332ce3
clean is a skill published in the GitHub repository samibs/skillfoundry (12 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 3,793 once invoked, about $0.0001 per session on Opus 5. 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.
Other skills, from other repositories
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
ring:applying-composition-patterns
React composition patterns that scale. Avoid boolean prop proliferation by using compound components, lifting state, and composing internals. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or during architecture review. Skip for simple components with 1-2 props…
ring:searching-code
Forensic code search and analysis with optional Chain of Draft (CoD) ultra-concise mode. Five-phase methodology (clarification, planning, execution, analysis, synthesis) with severity assessment. Use for targeted investigation of specific patterns, bugs, or vulnerabilities. Skip for broad architecture mapping (use…
ring:exploring-codebases
Exploring a codebase across phases: scopes the target, detects architecture, components, and layers, deep-dives each discovered perspective, then synthesizes findings into actionable guidance with file:line evidence. Use to understand how a feature or system works before planning changes, or to orient on an unfamiliar…
ring:auditing-dependency-security
Auditing a dependency for supply-chain risk before install (pip/npm/go/cargo): checks typosquatting, maintainer/age risk, vulnerability DBs (OSV, GHSA, Socket), and lockfile hash pinning, then emits a risk score and approve/conditional/escalate/block decision. Use when adding or updating a dependency, reviewing a…