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 instructions/samibs/skillfoundry/claude-mdgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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.
[](https://agentmods.dev/instructions/samibs/skillfoundry/claude-md)<a href="https://agentmods.dev/instructions/samibs/skillfoundry/claude-md"><img src="https://agentmods.dev/badge/instructions/samibs/skillfoundry/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.04926 | $0.04926 |
| Opus 5 | $0.02463 | $0.02463 |
| Sonnet 5 | $0.00985 | $0.00985 |
| Haiku 4.5 | $0.00493 | $0.00493 |
Grade C, and why
skillfoundry CLAUDE.md scanned grade C with 2 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 today.
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 .next node_modules/.cache Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:<port>/health | head -1 How it starts
The opening of the file, as written. The whole thing — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — SkillFoundry Framework Project Instructions
For universal AI agent rules (security, testing, LLM guardrails, workflow preferences): see
~/.claude/CLAUDE.mdFor production operations (PM2, caching, APM, migrations, incident response): seedocs/enterprise-standards.mdFor AI-specific security anti-patterns: seedocs/ANTI_PATTERNS_DEPTH.mdanddocs/ANTI_PATTERNS_BREADTH.mdFor environment pre-flight discipline (interpreter pinning, .env safety, diagnostic mode): seeagents/_env-preflight-protocol.mdFor codebase comprehension pre-flight (Code Map: contract surface, import graph, DB/layer map — runs before implementing): seeagents/_codemap-preflight-protocol.mdFor coding discipline (think-before-code, simplicity, surgical changes, goal-driven execution): seeagents/_coding-discipline.md
This file contains framework-specific rules only. General agent behavior is inherited from the global CLAUDE.md.
Philosophy
- Cold-blooded logic over flattery: No vague encouragement or optimistic assumptions — honest, structured, production-ready evaluations only.
- ONLY REAL LOGIC: No placeholders, no TODOs, no mocks, no stubs, no "coming soon", no fake data. Every feature must work end-to-end with real implementations.
- Three-Layer Completeness: Every feature must be verified across DATABASE → BACKEND → FRONTEND before it's considered done.
- PRD-First Development: Every non-trivial feature starts with a Product Requirements Document. No PRD = no implementation.
- Implement > Test > Iterate: Every feature must be tested before being considered done.
- Never break existing features: New features must not cause regressions.
- Document everything: All modules and changes must include developer- and user-level documentation.
- Clean project structure: When work is complete, organize files properly — root folder contains only essentials.
Mandatory Production Rules
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.
- today First seen · 493 lines · 4,926 tokens per session scan C ca03897906ef
skillfoundry CLAUDE.md is an instructions file published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It adds 4,926 tokens to every session, about $0.0246 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other instructions, from other repositories
plan-forge dapr.instructions.md
Dapr patterns for .NET — building blocks, component config, sidecar architecture, multi-tenant isolation, workflows, state management, secrets.
plan-forge architecture-principles.instructions.md
Core architecture principles — Architecture-First Approach, Separation of Concerns, TDD, Best Practices over Quick Wins. READ BEFORE any code changes.
plan-forge copilot-instructions.md
Copilot instructions for srnichols/plan-forge, covering instructions for copilot, architecture principles, core principles (non-negotiable), cost estimates and talking to forge-master.
plan-forge testing.instructions.md
Testing rules for Plan Forge — vitest patterns, fake-timers vs tolerance, mocking conventions, and how to read test output without hallucinating failures. Auto-loads when editing test files.
plan-forge auth.instructions.md
.NET authentication & authorization — JWT/OIDC, policy-based auth, multi-tenant isolation, API keys, testing.
plan-forge blazor-fluent-ui.instructions.md
Blazor Server + Microsoft Fluent UI patterns — component layering, state, lifecycle, accessibility. Auto-loads when editing .razor / .razor.cs files.