agentmods.dev

knowledge-layer

A deployment wrapper around RepoBrain, a system that builds a searchable knowledge graph from a project’s files. It refreshes the graph and answers questions using code, documentation, data, and media metadata.

In plain words
What is it for?
Use it to refresh repository knowledge files or ask questions about a workspace through `refresh_filesystem` and `ask_filesystem`, while keeping RepoBrain’s core architecture as the source of truth.
Why use it?
It gives agents project answers grounded in source paths instead of relying only on memory or manually opened files. If graph files are unavailable, it can fall back to basic project structure and conventions.

Skill for Claude CodeCodex

1.3k +1 3d ago A scan 42 tokens original MIT
View the source file study8677/repobrain
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 skills/study8677/repobrain/knowledge-layer
Any agent
npx skills add study8677/repobrain --skill knowledge-layer
Clone the repo
git clone --depth 1 https://github.com/study8677/repobrain

Made for: Claude Code, Codex.

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 299 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00042 $0.00299
Opus 5 $0.00021 $0.00150
Sonnet 5 $0.00008 $0.00060
Haiku 4.5 $0.00004 $0.00030

Measured yesterday against content hash 50de21c42cdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-layer 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.

The scan reads SKILL.md. This mod also ships 2 executable files (__init__.py, tools.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

engine/repobrain_engine/skills/knowledge-layer/SKILL.md · 38 lines

What it actually says

Knowledge Layer Skill

Purpose

Provide a high-level deployment wrapper over RepoBrain core, with graph-first knowledge injection and all-file support (code, docs, data, media metadata).

Inputs

  • refresh_filesystem(workspace=".", quick=False)
  • ask_filesystem(question, workspace=".")

Outputs

  • Refresh writes graph-first artifacts under .repobrain/:
    • knowledge_graph.json
    • knowledge_graph.md
    • knowledge_graph.mmd
    • document_index.md
    • data_overview.md
    • media_manifest.md
    • plus existing conventions.md and structure.md
  • Ask returns a grounded answer with source paths.

Boundaries

  • Skill is a wrapper layer only; no standalone runtime.
  • Core Hub/Agent/Pipeline architecture remains the source of truth.

Compatibility

  • Existing commands (rb-refresh, rb-ask, rb-mcp) remain valid.
  • High-level aliases can be disabled with RB_ENABLE_LAYER_ALIASES=0.

Degrade Strategy

  • If graph artifacts are unavailable, ask falls back to structure.md and conventions.md context.
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 38 lines · 42 tokens per session scan A 50de21c42cdb

Subscribe to this mod's changes

knowledge-layer is a skill published in the GitHub repository study8677/repobrain (1,321 stars, last pushed 3d ago), licensed MIT. It adds 42 tokens to every session and 299 once invoked, about $0.0002 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.

DevOps and cloudSecurityTestingagents-sdkai-agentclaude-codecode-intelligencecode-searchcodebase-qa
Related

Other skills, from other repositories

graph

Whole-codebase structural map of the codanna index as one self-contained HTML disc. Wedges per top-level module, concentric rings with hubs at the centre, hover or click a symbol to light its edge web, search, hide or highlight modules, brush a date range on the ribbon timeline (symbols dated by git blame), heatmap of…

bartolli/codanna · 131 tokens

x-ray

Deep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.

bartolli/codanna · 25 tokens

Sverklo Code Intelligence

Gives you deep codebase understanding — semantic search, blast-radius analysis, PR review, and health audits.

sverklo/sverklo · 27 tokens

gh-stack

Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.

sourcebot-dev/sourcebot · 65 tokens

codestory-grounding

Use when an agent should ground a local repository with CodeStory before making source claims, planning edits, choosing tests, reviewing changes, or using broad retrieval evidence through the CodeStory plugin MCP.

TheGreenCedar/CodeStory · 44 tokens

optimize-accuracy-first

Diagnose, design, implement, and validate system optimizations while treating correctness, retrieval quality, bounded behavior, and avoided downstream work as primary outcomes. Use for performance, latency, CPU, memory, storage, indexing, search, retrieval, caching, batching, concurrency, tokenizer, database, or…

morluto/leantoken · 90 tokens