Borrowing it
Nothing to install: this file belongs to djterry15-afk/coworkos-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/djterry15-afk/coworkos-template/main/CLAUDE.mdgit clone --depth 1 https://github.com/djterry15-afk/coworkos-templateWrote 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/djterry15-afk/coworkos-template/claude-md)<a href="https://agentmods.dev/instructions/djterry15-afk/coworkos-template/claude-md"><img src="https://agentmods.dev/badge/instructions/djterry15-afk/coworkos-template/claude-md/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/instructions/djterry15-afk/coworkos-template/claude-md"><img src="https://agentmods.dev/badge/instructions/djterry15-afk/coworkos-template/claude-md.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 | $0.02125 | $0.02125 |
| Opus 5 | $0.01063 | $0.01063 |
| Sonnet 5 | $0.00425 | $0.00425 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
coworkos-template 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 10d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoworkOS — Workspace Map
Auto-loaded every session. Map only — structure, routing, navigation. This is a denatured template. Replace the example workstations/projects with your own.
What This Is
A tiered, file-based workspace applying the Interpretable Context Methodology (ICM) for cross-domain reasoning and artifact production with an AI agent. The structure is the system: routing tables decide what to load, plain-text files are the memory, and human gates govern anything that writes durable state.
Tiers: ROOT → WORKSTATION → PROJECT → (WORKFLOW when a project matures).
Each tier has CLAUDE.md (L0 map + L1 routing) and CONTEXT.md (orient / current state).
At ROOT, CONTEXT.md also carries the operator contract (who you are, how you want the agent to
work, reliability/failure/memory protocols).
Architecture foundation: 00_Resources/references/tier-1-2-root-workstation-model.md.
Folder Structure
coworkos-template/
├── CLAUDE.md ← this file — auto-loaded every session (L0 map + L1 routing)
├── CONTEXT.md ← ROOT operator contract + current state — load every session
├── README.md ← outward-facing: what this template is + how to instantiate
├── 00_Resources/ ← cross-workstation reference layer
│ ├── cross-domain-map.md ← L1 orient — links across workstations; load for cross-domain questions
│ └── references/ ← Layer 3 — stable reference, load by trigger
│ ├── tier-1-2-root-workstation-model.md ← architecture foundation + ROOT/WORKSTATION conventions
│ ├── tier-3-project-model.md ← how to organize files within a project (the project KINDS)
│ ├── tier-4-workflow-model.md ← the WORKFLOW (pipeline-ICM) tier model + the three SHAPES
│ ├── decisions-log.md ← the design rationale (the "why" behind the template's shape)
│ ├── icm-paper.md ← distillation of the ICM source paper (Van Clief & McDermott)
│ ├── karpathy-llm-wiki.md ← distillation of the LLM Wiki pattern (Karpathy) the wiki uses
│ └── skills/ ← invokable procedures (session close, handoff, build spec, web capture)
├── Workstation_A_Writing/ ← EXAMPLE domain (subject-area) — the simple case: one project, one shape
│ ├── content-project/ ← Reasoning Workspace
│ │ └── content-factory/ ← tier-4 shape: content-production (staged-pipeline + hub)
│ └── forming-idea/ ← STATE example — a Forming stub (kind undetermined; structure not yet earned)
├── Workstation_B_Markets/ ← EXAMPLE domain — the COMPOSED case: one project runs the whole loop
│ └── market-thesis/ ← Reasoning Workspace — acquire → organize → monitor → conclude
│ ├── llm-wiki/ ← organizes sourced knowledge (Layer-3 store)
│ ├── research-factory/ ← tier-4 shape: research-acquisition (exploratory fan-in) — acquires
│ └── stress-monitor/ ← tier-4 shape: deterministic monitor (data → transform → report)
└── Workstation_C_Workbench/ ← EXAMPLE domain — the MIXED-KIND case: contrasting kinds side by side
├── reference-library/ ← Reference Repo — FLAT: consult / retrieve entries one at a time
├── reference-study/ ← Reasoning Workspace (study container) — synthesize ACROSS reference sub-projects
├── build-tool/ ← Build / Workflow — reasoning shell over a code body
└── retired-tool/ ← STATE example — a Dead own-reference (finished, retired; structure shed)
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.
- 10d ago First seen · 131 lines · 2,125 tokens per session scan A 343ca46d526c
coworkos-template CLAUDE.md is an instructions file published in the GitHub repository djterry15-afk/coworkos-template (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,125 tokens to every session, about $0.0106 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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 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).
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.