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 skills add FortiumPartners/ensemble --skill ensemble-fold-promptgit clone --depth 1 https://github.com/FortiumPartners/ensembleWrote 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/skills/fortiumpartners/ensemble/ensemble-fold-prompt)<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-fold-prompt"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-fold-prompt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-fold-prompt"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-fold-prompt.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00033 | $0.01582 |
| Opus 5 | $0.00016 | $0.00791 |
| Sonnet 5 | $0.00007 | $0.00316 |
| Haiku 4.5 | $0.00003 | $0.00158 |
Grade A, and why
ensemble-fold-prompt 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 13d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensemble Command: /ensemble:fold-prompt
This Codex skill mirrors the Ensemble slash command /ensemble:fold-prompt.
Follow the workflow below, adapt to the current repository, and keep outputs structured.
Analyze a project's codebase to extract coding conventions, optimize CLAUDE.md for minimal token cost and maximum AI productivity, and organize context with progressive disclosure. Every token in CLAUDE.md is loaded every session -- this command ensures none are wasted.
Workflow
Phase 1: Codebase Standards Discovery
1. Detect Technology Stack Identify languages, frameworks, package managers, and build tools
- Read package.json, Gemfile, requirements.txt, go.mod, mix.exs, *.csproj, or equivalent
- Identify primary language(s) and framework(s) (e.g., Next.js 14, Rails 7, Phoenix 1.7)
- Detect test framework(s) and runner commands
- Detect linter/formatter config (.eslintrc, .prettierrc, rustfmt.toml, .rubocop.yml)
- Note monorepo structure if present (workspaces, packages/, apps/)
2. Extract Coding Conventions Mine the codebase for patterns that an AI assistant must follow
- Sample 5-10 representative source files to detect naming conventions (camelCase vs snake_case, file naming)
- Check for barrel exports, path aliases, import ordering conventions
- Identify error handling patterns (Result types, try/catch style, custom error classes)
- Detect API patterns (REST routes, GraphQL resolvers, RPC definitions)
- Read existing CONTRIBUTING.md, .editorconfig, or style guides if present
- Check commit history for conventional commit usage and scope patterns
3. Build Standards Index Create a compact index of discovered standards for token-efficient reference
- Compile findings into a standards index -- one line per standard, format "standard-name: brief description"
- Group standards by category (naming, testing, imports, error-handling, git)
- Keep each entry under 80 characters -- the index is a lookup table, not documentation
- If the project already has a .ensemble/standards.yml or similar, merge rather than replace
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.
- 13d ago First seen · 142 lines · 33 tokens per session scan A c913ba5e2718
ensemble-fold-prompt is a skill published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,582 once invoked, about $0.0002 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
context-recovery
Recovers project handoff context from local Codex, Claude Code, Gemini, CodeBuddy, and codexmate-derived sessions. Use when the user asks what happened in prior project/PR/branch/file/error work, needs a handoff brief, wants old decisions or validations recovered, or asks to summarize cross-session project activity…
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
dev
This skill should be used when the user asks to start, restart, keep alive, or inspect the local pikiclaw development service, including npm run dev, local debug bot startup, dashboard verification, and dev log checks.
bmad-quick-dev-new-preview
Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.
bmad-create-story
Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]".
bmad-quick-dev
Implement a Quick Tech Spec for small changes or features. Use when the user provides a quick tech spec and says "implement this quick spec" or "proceed with implementation of [quick tech spec]".