Borrowing it
Nothing to install: this file belongs to fjpulidop/specrails-core. 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/fjpulidop/specrails-core/main/CLAUDE.mdgit clone --depth 1 https://github.com/fjpulidop/specrails-coreWrote 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/fjpulidop/specrails-core/claude-md)<a href="https://agentmods.dev/instructions/fjpulidop/specrails-core/claude-md"><img src="https://agentmods.dev/badge/instructions/fjpulidop/specrails-core/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/fjpulidop/specrails-core/claude-md"><img src="https://agentmods.dev/badge/instructions/fjpulidop/specrails-core/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 | $0.00783 | $0.00783 |
| Opus 5.5 | $0.00313 | $0.00313 |
| Sonnet 5.5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
specrails-core 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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
specrails-core
Agent workflow engine for specrails-desktop: a deterministic installer that renders the specrails workflow for Claude Code, Codex, Gemini CLI and Kimi Code, plus the programmatic agent runtime that executes implementations. Desktop is the only host; there is no standalone product surface.
Stack
| Layer | Tech |
|---|---|
| CLI + installer | TypeScript (ESM, strict), Node ≥ 20.19.0, macOS/Linux/Windows |
| Runtime | @langchain/langgraph state graph, provider CLI executors, OpenAI-compatible chat loop |
| Specs | OpenSpec (pinned in pinned-versions.json) |
| Tests | vitest (OS × Node CI matrix) |
Layout
bin/specrails-core.mjs npm bin shim → dist/installer/cli.js
src/installer/
cli.ts single dispatcher: init, install-framework, swap-current, assemble, pipeline, rules, runtime
commands/ init + offline framework lifecycle
phases/ prereqs, provider detection, scaffold (provider rendering), manifest, install-config
util/ fs, exec, git, registry, install transaction, logger
src/pipeline/pipeline-state.ts pipeline journal, gates and verification receipts; Node built-ins only because it is copied into projects as .specrails/runtime/pipeline-state.mjs
src/agent-runtime/ runtime: workflow engine, graph nodes/roles, executors, compact loop, recovery, CLI, project rules inventory (.specrails/rules.json)
src/shared/ helpers shared by the CLIs (argument parsing, Specrails home, secret redaction)
templates/ implement/retry commands, provider settings, Kimi runner (roles are runtime-defined, never templated)
integration-contract.json Desktop ⇄ Core contract (schemaVersion 5.9)
Commands
npm ci
npm run build # src/ → dist/
npm test # build + typecheck + vitest
npm run ci # typecheck, script tests, coverage, package check
Conventions
- Dependency direction is
shared ← pipeline ← agent-runtime ← installer, enforced bysrc/architecture.test.ts. The installer loads the runtime lazily for theruntimecommand only. - The agent session runtime (
src/agent-runtime/session/) is layereddomain ← application ← drivers | journal | host ← index.ts ← cli.ts; provider vocabulary stays in its driver folder. See docs/agent-sessions/architecture.md. - Conventional commits (
feat:,fix:,docs:,chore:); kebab-case files; tests next to their subject as*.test.ts. - Spawn processes through
src/installer/util/exec.tsorsrc/agent-runtime/cli-process.ts(Windows quoting and tree-kill); never assume POSIX paths. templates/commands/specrails/*.mdare the single source for every provider's workflow entry points.- Any change to the files Desktop reads (
integration-contract.json, CLI flags,.specrails/runtime/*, runtime status JSON) needs a paired Desktop change.
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.
- 4d ago Changed · +12 tokens per session 6e92981acaa8
- 7d ago Changed · +8 tokens per session e766a80d0013
- 21d ago Changed · +1 lines · +60 tokens per session 525ff543efa7
- 23d ago Changed · +36 tokens per session cf0f0c5acbab
- 1mo ago Changed · -4 tokens per session 98520be45082
- 1mo ago Changed · -82 lines · -1,202 tokens per session cf0efdb166f6
- 2mo ago First seen · 134 lines · 1,873 tokens per session scan A 3295e407b01c
specrails-core CLAUDE.md is an instructions file published in the GitHub repository fjpulidop/specrails-core (9 stars, last pushed 4d ago), licensed MIT. It adds 783 tokens to every session, about $0.0031 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.