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 rules/varutasu/agent-pipeline/agent-context-bootstrapgit clone --depth 1 https://github.com/varutasu/agent-pipelineWhat 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 | $0.00410 | $0.00410 |
| Opus 5 | $0.00205 | $0.00205 |
| Sonnet 5 | $0.00082 | $0.00082 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
agent-context-bootstrap 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 2d 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.
What it actually says
Agent context bootstrap
If the current workspace has no AGENTS.md at the repo root and no .cursor/rules/ directory, and the user is asking how to orient themselves in this codebase, set up AI guidance, reduce token use, deploy agent context, or scaffold rules and skills, suggest the bootstrap-agent-context skill before answering at length.
Phrase it as a one-line offer:
"This repo doesn't have an
AGENTS.mdor.cursor/rules/yet. I can run thebootstrap-agent-contextskill to draft them — it detects the stack and stops before committing for your review. Want me to start?"
Then wait for confirmation before reading the skill.
When NOT to suggest
- The repo already has
AGENTS.mdor.cursor/rules/*.mdc. (The skill is for first-time setup.) - The user is asking a narrow code question that doesn't depend on broad orientation.
- The user has explicitly declined the bootstrap in this conversation.
- The repo is clearly read-only or not the user's (vendored, cloned for reference, third-party).
This is a soft nudge, not a hard requirement. If grep + read solves the user's question in one or two calls, do that instead.
If the repo IS already bootstrapped
If the workspace has .agent-context-manifest.yml at the root and the user asks about updates, pipeline version, drift, or out-of-date rules/skills/agents, suggest the sync-agent-context skill instead:
"This repo has an agent-pipeline manifest at version X. I can run the
sync-agent-contextskill to compare each installed artifact against the latest pipeline source and propose updates per file. Want me to start?"
Same soft-nudge etiquette — skip if the question doesn't depend on freshness.
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.
- 2d ago First seen · 32 lines · 410 tokens per session scan A deb3df52cdd7
agent-context-bootstrap is a cursor rule published in the GitHub repository varutasu/agent-pipeline (2 stars, last pushed 23d ago), licensed MIT. It adds 410 tokens to every session, about $0.0020 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 cursor rules, from other repositories
cuopt-skill-evolution
Trigger skill evolution — after solving non-trivial problems, propose skill updates.
cursorrules
See CLAUDE.md for full context. Quick rules.
moyu
当检测到过度工程模式时自动激活：修改用户未要求的代码、创建不必要的抽象层、 添加未要求的注释/文档/测试、引入不必要的依赖、重写整个文件而非最小编辑、 diff 超出请求范围。用户说"太多了"、"只改 X"、"简单点"时触发。 Activates on over-engineering: modifying unrequested code, unnecessary abstractions, unsolicited comments/docs/tests, unrequested dependencies, full file rewrites, scope-exceeding diffs. Triggers on "too…
cursorrules
This repository contains a structured skill library for AI-assisted product development. Skills are in skills//SKILL.md. Read the relevant SKILL.md before generating any artifact.
cursorrules
AgentAnycast is a decentralized P2P runtime for the A2A (Agent-to-Agent) protocol.
homunculus
Homunculus self-evolving AI assistant. Use when user asks about evolution cycles, goal trees, system status, instincts, or skills. Provides routing to detailed evolution workflows.