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/paleo/alignfirst/agents-mdgit clone --depth 1 https://github.com/paleo/alignfirstWhat 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 | $0.00915 | $0.00915 |
| Opus 5 | $0.00458 | $0.00458 |
| Sonnet 5 | $0.00183 | $0.00183 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
alignfirst AGENTS.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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Always ignore the .plans, .local and .local-wt directories when searching the codebase.
Tooling
Package manager: npm workspaces (root package.json declares "workspaces": ["packages/*"]).
Runtime: Node (ESM only, "type": "module").
Language: TypeScript with strict: true, module: NodeNext. Each package has a tsconfig.build.json (emits dist/) and a tsconfig.json (noEmit, includes src + test).
Linter / formatter: Biome (biome.json at root). npm run lint / npm run lint:fix.
Test runner: Vitest (vitest run). Per-package: npm test --workspace <name>. All packages: npm test.
Releases: Changesets (.changeset/). Base branch: main. Default access: public. Publishing runs from CI through npm trusted publishing — see docs/releasing.md.
Workspace scripts (root): build, test, clear, lint, lint:fix — all fan out to packages via npm run <name> --workspaces --if-present.
This repository is on GitHub.
Packages
@paleo/alcode— coding agent wrapper for the AlignFirst developer.@paleo/alproject— local project registry for the AlignFirst developer@paleo/docmap— lightweight documentation system for AI agents and humans@paleo/openclaw-channel-mock-core— shared library for synthetic OpenClaw channel plugins (bus, actions, factories)@paleo/openclaw-slack-mock— Slack-shaped channel plugin for test scenarios@paleo/openclaw-discord-mock— Discord-shaped channel plugin for test scenarios@paleo/openclaw-test— Dockerised regression-test harness (bus, scenario driver, judge, Compose stack)@paleo/plans-share— share the.plansdirectory through a team plans repository@paleo/workspace— run multiple git-worktree dev environments side by side
Docmap - Seek Documentation
Before any investigation or code exploration, run npm run docmap, then read the relevant documentation. Mandatory for every task.
Workspaces
A workspace is a git worktree (with its branch) plus its own dev setup: symlinked shared directories and seeded config files. Workspaces are isolated, so you can work on several branches in parallel. This repository has no dev server, so the system runs portless: nothing to start, no dev script.
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 · 71 lines · 915 tokens per session scan A 81eb07e64b0e
alignfirst AGENTS.md is an instructions file published in the GitHub repository paleo/alignfirst (85 stars, last pushed 2d ago), licensed CC0-1.0. It adds 915 tokens to every session, about $0.0046 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 instructions, from other repositories
claude-code-best-practice CLAUDE.md
Claude Code instructions for shanraisshan/claude-code-best-practice, covering claude.md, repository overview, key components, weather system (example workflow) and skill definition structure.
youtube-tutorials AGENTS.md
Instructions for owainlewis/youtube-tutorials, covering repository instructions, before editing, create a tutorial, tutorial standards and writing standards.
codex-cli-best-practice AGENTS.md
Instructions for shanraisshan/codex-cli-best-practice, covering agents.md, what this is, architecture, orchestration flow and key directories.
claude-code-hooks CLAUDE.md
Instructions for shanraisshan/claude-code-hooks, covering claude code hooks, project structure, critical: hook count consistency, agent hooks and workflows.
ng-agentic AGENTS.md
Instructions for L-X-T/ng-agentic, covering role & project context, agent behavior & workflow, typescript best practices, modern angular (v22+) standards and component architecture.
ng-agentic copilot-instructions.md
Instructions for L-X-T/ng-agentic, covering copilot instructions and copilot-specific.