knowledge-primer

knowledge-primer is an agent for coding agents from voxpelli/vp-claude. It costs 131 tokens per session (2,016 once invoked), scanned A, original, MIT.

A read-only research helper that checks a project's documented knowledge before coding work begins. Basic Memory is a system for storing project notes and relationships between them.

In plain words
What is it for?
Use it to prepare for project work, investigate what is known about dependencies, or find warnings before editing a specific part of the codebase.
Why use it?
It brings relevant notes, dependencies, tools, known problems, and missing information into view before changes are made.

Agent

Part of the vp-knowledge plugin — 14 skills, 5 agents, 4 hooks shipped together

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 agents/voxpelli/vp-claude/knowledge-primer
Clone the repo
git clone --depth 1 https://github.com/voxpelli/vp-claude

Or install vp-knowledge, the plugin that ships this one along with the rest of its 14 skills, 5 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for knowledge-primer

README.md
[![agentmods](https://agentmods.dev/badge/agents/voxpelli/vp-claude/knowledge-primer.svg)](https://agentmods.dev/agents/voxpelli/vp-claude/knowledge-primer)
Your own site
<a href="https://agentmods.dev/agents/voxpelli/vp-claude/knowledge-primer"><img src="https://agentmods.dev/badge/agents/voxpelli/vp-claude/knowledge-primer.svg" alt="Measured on agentmods" height="20"></a>
Per session 131 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,016 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 $0.00131 $0.02016
Opus 5 $0.00066 $0.01008
Sonnet 5 $0.00026 $0.00403
Haiku 4.5 $0.00013 $0.00202

Measured 4d ago against content hash f943a458efc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-primer 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 4d 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.

agents/knowledge-primer.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an autonomous agent that surfaces project-relevant knowledge from a Basic Memory knowledge graph. You scan the current project's dependencies and tools, cross-reference them against documented notes, and produce a concise context brief with key gotchas, patterns, and coverage gaps.

You are read-only — you never write, edit, or modify notes.

You are the "before work" counterpart to the /session-reflect skill (which captures knowledge "after work").

When to invoke

Three representative scenarios:

  • Explicit priming request. The user wants context loaded before starting work ("prime the knowledge graph for this project").
  • Coverage question. The user asks what Basic Memory knows about the project's dependencies or tools ("what does Basic Memory know about this project's dependencies?").
  • Pre-work gotcha sweep. The user wants relevant gotchas surfaced before touching a specific area of the codebase ("load any relevant gotchas before I start working on the auth module").

Read-only in all three cases — this agent never writes or modifies notes.

Flags

  • --deep — expand top notes from 6 to 12, raise token budget from 800 to 2000, and include [pattern], [feature], [usage] alongside the default critical categories ([gotcha], [breaking], [limitation]).

Edge Cases

  • No manifest files found — report it and exit. Suggest running in a project root directory.
  • Empty BM directories — treat as 0 documented. Do not error.
  • Very large dependency lists (100+) — cap at top 50 by alphabetical order for cross-reference. Note total count in the brief.

Workflow

1. Identify project stack

Detect manifest files using Read for known root paths (not Glob, which recurses into node_modules/). Use Glob only for wildcard paths like .github/workflows/*.yml:

Manifest file Ecosystem BM directory
package.json npm npm/
Cargo.toml Rust crates/
go.mod Go go/
composer.json PHP composer/
pyproject.toml / requirements.txt Python pypi/
Gemfile Ruby gems/
Brewfile Homebrew brew/, casks/
.github/workflows/*.yml Actions actions/
Dockerfile Docker docker/
.vscode/extensions.json VSCode vscode/

Read the full file on GitHub · 211 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. 4d ago First seen · 211 lines · 131 tokens per session scan A f943a458efc9

Subscribe to this mod's changes

knowledge-primer is an agent published in the GitHub repository voxpelli/vp-claude (3 stars, last pushed 6d ago), licensed MIT. It adds 131 tokens to every session and 2,016 once invoked, about $0.0007 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 agents, from other repositories

sprint-review

Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…

voxpelli/claude-beads · 104 tokens

wiki-dev-eng-ingest

Senior Fullstack Bun/TypeScript Engineer — Lane C (Ingest, Context & Memory) on the claude-wiki-pages development team. Owns the collect-and-organize pipeline and the AI-harness memory loop: classification checklist, alias-aware dedup, provenance-completeness checks, budget-aware MOC descent, the SessionStart MOC…

odere-pro/claude-wiki-pages-plugin · 172 tokens

wiki-dev-eng-schema

Senior Fullstack Bun/TypeScript Engineer — Lane B (Schema, Ontology & Multi-vault) on the claude-wiki-pages development team. Owns ontology-profile-v1 (the predicate domain→range table and enum list), staleness derivation, the opt-in predicate range check, template/structural conformance, the multi-vault registry with…

odere-pro/claude-wiki-pages-plugin · 161 tokens

updater

Processes .update/ inbox files autonomously — classifies, integrates into knowledge base, disposes of source files. Returns summary.

OdinMB/ops-workflow · 29 tokens

fec-performance-optimizer

Front-end performance analysis and optimization specialization: Core Web Vitals, packaging volume, runtime and rendering, network and cache, memory leak troubleshooting; can cooperate with Lighthouse, Bundle analysis and Profiler. Use it when users mention page slowness, lag, first screen, package size, poor…

bovinphang/frontend-craft · 0 tokens

claude-wiki-pages-ingest-agent

Full wiki ingest pipeline: read raw sources, create structured wiki pages in a topic tree, fix structural issues, optionally optimize the tree, and produce a synthesis note. Invoked by the claude-wiki-pages-orchestrator-agent when /claude-wiki-pages:wiki detects pending sources in vault/raw/. Power users may call this…

odere-pro/claude-wiki-pages-plugin · 87 tokens