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/therealclodius/fram-loop/claude-mdgit clone --depth 1 https://github.com/TheRealClodius/fram-loopWhat 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 | $0.01975 | $0.01975 |
| Opus 5 | $0.00988 | $0.00988 |
| Sonnet 5 | $0.00395 | $0.00395 |
| Haiku 4.5 | $0.00198 | $0.00198 |
Grade A, and why
fram-loop CLAUDE.md 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fram-loop — agent instructions
This repo is the source of the fram-loop skill — a two-agent autonomous loop (Builder + Reviewer + Orchestrator) for shipping multi-phase coding deliverables. The skill itself is at skills/fram-loop/SKILL.md. This CLAUDE.md is for agents working on the skill (editing it, releasing it, evaluating it), not for agents running the skill on a project.
Repo layout
fram-loop/
├── LICENSE
├── README.md # user-facing skill description, install instructions, lineage
├── EVALS.md # eval retrospective (per-run findings + improvement proposals)
└── skills/
└── fram-loop/
├── SKILL.md # the skill — protocol, defaults, phase structure, rubric
└── references/
└── templates.md # Builder + Reviewer prompt scaffolds
Keep root minimal. Per-eval test deliverables (e.g. The Margin) live as standalone repos under ~/Documents/Projects/fram-ateliers/, not in this repo. Do not commit site/, deliverable folders, or scratch worktrees here — gh skill install only ships skills/fram-loop/ to install users, but anyone browsing or cloning the repo would see clutter.
Release process — read before tagging
The canonical installer is gh skill install (built into gh ≥ 2.90, shipped April 2026, validates against the agentskills.io spec). Two non-obvious things about its resolver:
- Tag ≠ Release.
gh skill install TheRealClodius/fram-loop fram-loop(no version pin) resolves to the latest GitHub Release, NOT the latest pushed tag. A tag with no Release is invisible to the resolver. Always cut a Release alongside the tag. - Bundled assets ride along — but only if they exist at the tagged commit.
references/templates.mdis part of the skill. If you tag a commit that predates a bundled asset, install users get a stale skill missing that asset. Tag late, not early.
Cutting a release
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 · 108 lines · 1,975 tokens per session scan A fb3e08252b07
fram-loop CLAUDE.md is an instructions file published in the GitHub repository TheRealClodius/fram-loop (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,975 tokens to every session, about $0.0099 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 2026-08-31.
Other instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.