stackshift AGENTS.md

Repository instructions for StackShift, a project that helps experienced developers learn unfamiliar technologies quickly. The file explains the project’s purpose, product principles, and development workflow.

In plain words
What is it for?
Use it when working in the StackShift repository to understand its goals, read required background documents, and follow its skill-authoring and development practices.
Why use it?
It gives coding agents the project context and rules they need before changing StackShift, reducing decisions based on incomplete or invented assumptions.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/yingsun1004/stackshift/agents-md
Clone the repo
git clone --depth 1 https://github.com/YingSun1004/stackshift

Made for: Codex, OpenCode.

Per session 436 This file is loaded in full into every session.
When invoked 436 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00436 $0.00436
Opus 5 $0.00218 $0.00218
Sonnet 5 $0.00087 $0.00087
Haiku 4.5 $0.00044 $0.00044

Measured yesterday against content hash 8c5228541339, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

stackshift 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.

AGENTS.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

StackShift Repository Guidance

Project purpose

StackShift is an AI-powered rapid technical skill-transfer workflow for experienced developers and technical professionals who need to become useful with an unfamiliar technology quickly.

Before making product or architecture decisions, read:

  1. docs/INTRODUCTION.md
  2. docs/history/IMPLEMENTATION_PLAN.md
  3. README.md

Product principles

  • Optimize for the shortest defensible path to a concrete outcome: work-ready, interview-ready, project-ready, or a stated combination.
  • Begin with the learner's existing technical knowledge. Do not teach from zero unless a real prerequisite gap is identified.
  • Convert familiar concepts into explicit mappings to the target technology.
  • Separate direct transfer, partial transfer, genuinely new knowledge, and misleading similarities.
  • Prefer active practice and evidence over passive explanations and self-reported confidence.
  • Keep the learning path narrow. Defer advanced or low-value material unless it is required by the learner's goal.
  • Do not fabricate readiness scores, current APIs, interview expectations, or project conventions.
  • When the target technology is version-sensitive, prefer official primary documentation.

Skill-authoring rules

  • The first release is an instruction-only Codex skill.
  • Keep .agents/skills/stackshift/SKILL.md concise and operational.
  • Put detailed rubrics, templates, and reusable guidance in references/ rather than expanding SKILL.md indefinitely.
  • Do not add scripts until a repeated deterministic task clearly justifies one.
  • Do not modify a learner's repository or create persistent learning-state files unless the request implies an ongoing learning workflow or the user approves persistence.
  • Every meaningful behavior change must be represented by at least one evaluation prompt.
  • Include both positive trigger cases and negative controls in evals.

Development workflow

  • Make small, reviewable changes.
  • Update docs/history/IMPLEMENTATION_PLAN.md when a milestone, scope decision, or architecture decision changes.
  • Record recurring agent mistakes as repository guidance or eval cases instead of relying on conversational memory.
  • Use the Playwright learning journey as the first dogfooding case, but keep the core workflow technology-agnostic.

Read the full file on GitHub · 40 lines

Changes

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.

  1. yesterday First seen · 40 lines · 436 tokens per session scan A 8c5228541339

Subscribe to this mod's changes

stackshift AGENTS.md is an instructions file published in the GitHub repository YingSun1004/stackshift (1 stars, last pushed 9d ago), licensed MIT. It adds 436 tokens to every session, about $0.0022 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.

Related

Other instructions, from other repositories