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-discover-standardsgit 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-discover-standards)<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-discover-standards"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-discover-standards/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-discover-standards"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-discover-standards.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 | $0.00035 | $0.01309 |
| Opus 5 | $0.00017 | $0.00655 |
| Sonnet 5 | $0.00007 | $0.00262 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
ensemble-discover-standards 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 11d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ensemble Command: /ensemble:discover-standards
This Codex skill mirrors the Ensemble slash command /ensemble:discover-standards.
Follow the workflow below, adapt to the current repository, and keep outputs structured.
Analyze a project codebase to extract coding conventions, naming patterns, error handling styles, test structures, and git commit practices. Write discovered standards to a standards/ directory with a machine-readable index.yml for token-efficient reference by future agent sessions. Always merge with existing standards rather than replacing them.
Workflow
Phase 1: Codebase Scan
1. Tech Stack Detection Identify the primary language, framework, test framework, and tooling
- Read package.json, Gemfile, requirements.txt, go.mod, mix.exs, *.csproj, or equivalent manifest files
- Identify primary language(s) and framework(s) (e.g., Next.js 14, Rails 7, Phoenix 1.7, ASP.NET Core 8)
- Detect test framework(s) from devDependencies, Gemfile, or test directory conventions
- Detect linter/formatter config (.eslintrc, .prettierrc, rustfmt.toml, .rubocop.yml, .editorconfig)
- Note monorepo structure if present (workspaces, packages/, apps/)
- Print detected stack summary before proceeding
2. Convention Extraction Sample representative source files to identify project-specific coding patterns
- Sample 5-10 representative source files from src/, lib/, app/, or equivalent
- Detect naming conventions (camelCase vs snake_case, PascalCase for classes, file naming patterns)
- Check for barrel exports, path aliases, and import ordering conventions
- Identify error handling patterns (Result types, try/catch style, custom error classes)
- Detect API patterns (REST routes, GraphQL resolvers, RPC definitions, controller conventions)
- Identify test file naming conventions (*.spec.ts, *_test.go, spec.rb, test.py)
- Run git log --oneline -20 to detect commit style (conventional commits, scope patterns)
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.
- 11d ago First seen · 113 lines · 35 tokens per session scan A d282e392c48b
ensemble-discover-standards is a skill published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,309 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
bmad-code-review
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code".
bmad-review-edge-case-hunter
Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.
joycraft-design
Design discussion before decomposition — produce a 200-line design artifact for human review, catching wrong assumptions before they propagate into specs.
joycraft-spec-done
Lightweight per-spec wrap-up — bump status to in-review, terse discovery if surprised, commit. Run after each spec in checkpoint/isolated mode; no validation, no push, no PR.
code-review-loop
Run a scored, converge-or-cap code-review loop on a diff or surface — a read-only critic raises evidence-backed findings, a read-write fixer addresses only those findings, then re-audit until two clean rounds or a cap. Use when reviewing a PR, hardening a changed file, or iterating to a clean bill of health without…
skill-dev
Code quality audit: detect cross-module coupling, N+1 queries, dead exports, antipatterns, over-large components. Cross-checks against refactoring backlog.