Install
$ agentstack add skill-gustavo-meilus-superpipelines-sk-hierarchical-context ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
Hierarchical Context Maps — Distributed Architecture Context
> Distributes architectural knowledge across the repository by placing a PIPELINE-CONTEXT.md in each significant subdirectory. Agents operating within a directory acquire scope-relevant context automatically, conserving tokens and improving reasoning focus.
The Hierarchical Context system places localized PIPELINE-CONTEXT.md files throughout the project tree rather than centralizing knowledge in a single large file. An agent working in src/api/ loads only the context relevant to that directory instead of an entire monolithic prompt.
A localized markdown file (PIPELINE-CONTEXT.md) describing the purpose and boundaries of its resident directory. The recursive process of generating context maps for all significant project directories.
Protocol Execution
1. DIRECTORY TRAVERSAL
- Identify all significant architectural boundaries (e.g.,
src/,components/,api/,utils/). - Skip ignored directories (e.g.,
node_modules/,.git/,dist/).
2. CONTEXT GENERATION
For each significant directory, create a PIPELINE-CONTEXT.md adhering to LLM-readability standards (Scribius format):
- H1-First & Summary: Begin with an H1 header (
# Directory Name) followed immediately by a blockquote summary (>). - Cache-Stable Ordering: Place static context (purpose, constraints) before volatile elements.
- XML-Anchored Content: Wrap structured information in semantic XML envelopes:
- ``: A concise summary of what the directory does.
- ``: Specific rules (e.g., "no database access in components").
- ``: Bulleted list of primary modules and their responsibilities.
- ``: How the directory interacts with the broader system.
- Voice & Tone: Third-person impersonal voice, positive scoping, and unambiguous noun anchors (never "this" or "it" without a preceding noun). Preambles omitted.
3. ROOT CONTEXT INJECTION
- Generate a root-level
PIPELINE-CONTEXT.mdthat serves as the entry point, detailing the overall system architecture and linking to subdirectory context maps.
4. MAINTENANCE
- When files are significantly refactored during pipeline execution, flag the relevant
PIPELINE-CONTEXT.mdfor a required update.
- NEVER generate a single monolithic context file; always distribute context hierarchically.
- ALWAYS respect
.gitignorewhen traversing the repository. - Context maps remain concise and free of redundant code snippets; summaries replace inline code.
- ALWAYS format
PIPELINE-CONTEXT.mdfiles according to Scribius standards (XML envelopes, H1-first, impersonal voice).
Reference Files
${CLAUDE_PLUGIN_ROOT}/skills/sk-pipeline-paths/SKILL.md— Path resolution guidelines.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: gustavo-meilus
- Source: gustavo-meilus/superpipelines
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.