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/lexlapax/allbert-assist/agents-mdgit clone --depth 1 https://github.com/lexlapax/allbert-assistWrote 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/lexlapax/allbert-assist/agents-md)<a href="https://agentmods.dev/instructions/lexlapax/allbert-assist/agents-md"><img src="https://agentmods.dev/badge/instructions/lexlapax/allbert-assist/agents-md.svg" alt="Measured on agentmods" 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 | $0.03346 | $0.03346 |
| Opus 5 | $0.01673 | $0.01673 |
| Sonnet 5 | $0.00669 | $0.00669 |
| Haiku 4.5 | $0.00335 | $0.00335 |
Grade A, and why
allbert-assist 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 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Allbert is an Elixir/OTP assistant runtime with Phoenix interfaces and Jido at the agent/action layer. LiveView is an interface over the runtime, not the architecture center. The center is the runtime/action spine, Security Central, Settings Central, markdown-first memory, plugins, channels, public protocols, and Allbert Home.
Keep this file compact. It loads into every agent's context every session, so a
line here is paid by everyone, forever. Add a rule only when an agent would act
wrongly without it in context. Rationale, tables, diagrams, examples, and history
go in the authority doc and are pointed to, never inlined here. Route detail to
DEVELOPMENT.md (setup and environment), docs/developer/test-strategy.md
(gates, lanes, release mechanics), docs/developer/agent-context-map.md
(subsystem routing), docs/developer/<subsystem>.md (subsystem contracts),
docs/adr/ (decisions and consequences), docs/plans/ (release scope), and
docs/operator/ (operator procedure). Before adding, check whether an existing
rule should be strengthened instead — a second rule on the same subject is drift,
not coverage.
Reading Order
Before implementation work:
DEVELOPMENT.mddocs/plans/roadmap.md- The active milestone plan in
docs/plans/ - The matching request-flow document, when one exists
- ADRs that constrain the task
- Targeted
CHANGELOG.mdentries when shipped history matters - Relevant code and tests before editing
Use docs/developer/agent-context-map.md only for deeper subsystem routing or
released-version context. Do not bulk-read historical plans.
Authority
When sources conflict, use this order:
- Current user request
- Code and tests
- Active milestone plan and request-flow
- ADRs
docs/plans/roadmap.mdCHANGELOG.md- Historical plans and archives
Flag conflicts instead of silently following stale guidance. The vision document is the north star, not a release-scope source.
Context Discipline
- Load the smallest useful context.
- Prefer active plans, ADRs, focused changelog entries, and local code over broad document sweeps.
- For architecture or readiness work, zoom out to the roadmap/vision/ADRs first, then zoom back into the relevant files.
- Use
docs/developer/test-strategy.mdfor gate and lane classification. - Use
docs/developer/surface-contract.mdanddocs/developer/web-design-system.mdfor v0.58 surface/web work.
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 First seen · 252 lines · 3,346 tokens per session scan A 80ccde6657a8
allbert-assist AGENTS.md is an instructions file published in the GitHub repository lexlapax/allbert-assist (11 stars, last pushed 19d ago), licensed Apache-2.0. It adds 3,346 tokens to every session, about $0.0167 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
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.
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.