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/aligndottech/align-cli/claude-mdgit clone --depth 1 https://github.com/aligndottech/align-cliWhat 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 | $0.01482 | $0.01482 |
| Opus 5 | $0.00741 | $0.00741 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
align-cli 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 yesterday.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Setup for Align CLI
@aligndottech/cli - the open-source TypeScript CLI for Align (login, setup, connector imports, ask, MCP config). Companion to the closed align-stack gateway.
Workflow (Research → Plan → Implement → Validate, mandatory TDD)
For any non-trivial change, follow the same harness as align-stack: understand the area, write a reviewable plan, then RED → GREEN → REFACTOR. See .claude/rules/tdd.md in align-stack for the TDD cycle (test behaviors via the public API, mock only at module boundaries, never skip RED).
Linear-Driven Workflow (always)
Every substantial change is tracked in Linear and traceable branch → ticket → PR (trivial typo fixes exempt):
- Ticket first in the Align team (project Align MVP), label
align-cli. - Branch off latest
main, namedtnk/ALI-<#>(e.g.tnk/ALI-103). One branch / one PR per ticket. - Reference the ticket id (ALI-##) in the PR title or body.
- Linear MCP is configured in align-stack's
.mcp.json; reconnect if its tools aren't available.
Repo specifics (READ THIS)
- Package manager:
npm(NOT pnpm). The lockfile ispackage-lock.json. Usenpm install/npm ci- do not introducepnpm-lock.yaml. - Node ≥ 22.16 (CI's required
testjob runs the floor, 22.16;test-node24runs the other end). The floor isnode:sqlite, whichsrc/lib/local-db.tsuses for the local graph - unflagged from 22.13, andDatabaseSync.isTransactionlands in 22.16. There is no native dependency left, which is what lets one runner cross-compile all 8 binary targets (ALI-740). - Publishing happens when the RELEASE PR merges, not when you push a tag. There is no
publish.yml(this line used to name one): thepublishjob lives in.github/workflows/release-please.yml, is gated onneeds.release-please.outputs.releases_created == 'true', and runs typecheck, test and build beforenpm publish --provenance --access public. So the whole release is: land your work onmain, then merge thechore(main): release cli X.Y.ZPR that release-please opens. - This package is 0.x, and
bump-minor-pre-majoris set so aBREAKING CHANGE:footer bumps the MINOR (0.22 -> 0.23) instead of proposing 1.0.0. Without it, ALI-740's Node-floor bump silently retitled the open release PR torelease cli 1.0.0- a promise about API stability made by a commit footer, on a package whose own README says "Beta, pre-1.0".bump-patch-for-minor-pre-majoris deliberately NOT set: features should still bump the minor. Going to 1.0.0 is a decision someone makes, not a side effect. Do not publish manually, and do not hand-push a tag - the tag release-please creates is component-prefixed (cli-v0.19.0), so av*trigger would not match it even if one existed. Merging is not shipping: verify withnpm view @aligndottech/cli version, which lags the merge by a few minutes. bin.align → ./dist/index.js;files: ["dist", "README.md"]. Build withnpm run build(tsc).- Running a local build:
alignon PATH is the globally installed package, not your working tree. To test changes, runnode dist/index.js …(afternpm run build) or reinstall:npm run build && npm pack && npm i -g ./aligndottech-cli-*.tgz --force.
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.
- yesterday First seen · 91 lines · 1,482 tokens per session scan A 3de320f5d9a8
align-cli CLAUDE.md is an instructions file published in the GitHub repository aligndottech/align-cli (1 stars, last pushed 2d ago), licensed MIT. It adds 1,482 tokens to every session, about $0.0074 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.
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).
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.