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/yingsun1004/stackshift/agents-mdgit clone --depth 1 https://github.com/YingSun1004/stackshiftWhat 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 | $0.00436 | $0.00436 |
| Opus 5 | $0.00218 | $0.00218 |
| Sonnet 5 | $0.00087 | $0.00087 |
| Haiku 4.5 | $0.00044 | $0.00044 |
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.
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:
docs/INTRODUCTION.mddocs/history/IMPLEMENTATION_PLAN.mdREADME.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.mdconcise and operational. - Put detailed rubrics, templates, and reusable guidance in
references/rather than expandingSKILL.mdindefinitely. - 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.mdwhen 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.
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 · 40 lines · 436 tokens per session scan A 8c5228541339
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.
Other instructions, from other repositories
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
notebooklm-skill AGENTS.md
Instructions for claude-world/notebooklm-skill, covering notebooklm-skill, authentication, cli commands, notebooklm-skill — core operations and notebooklm-pipeline — workflow orchestration.
recursive-decomposition-skill AGENTS.md
Instructions for massimodeluisa/recursive-decomposition-skill, covering agents: recursive-decomposition skill, read these first (mandatory), language policy, non-negotiables and commands.
stockbit-mcp CLAUDE.md
Instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.
devin-handoff AGENTS.md
Instructions for club-cog/devin-handoff, covering devin handoff — agent guide, what this is, when to hand off, finding the script and how to use.
agent-plugins-skills copilot-instructions.md
Instructions for richfrem/agent-plugins-skills, covering copilot instructions for agent-plugins-skills, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.