agentmods.dev

veridge AGENTS.md

A project instruction file for coding agents working on Veridge, a tool that builds a searchable map of a software project for people and AI assistants. It sets the project’s design rules, setup steps, tests, and code layout.

In plain words
What is it for?
Use it when modifying Veridge, running its checks, adding tests, or deciding where new code belongs.
Why use it?
It gives agents the project context and constraints they need before making changes, reducing the risk of broken tests, extra dependencies, or unwanted edits to source files.

Instructions file for CodexOpenCode

1 2mo ago A scan 511 tokens original MIT
View the source file galimar/veridge
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 instructions/galimar/veridge/agents-md
Clone the repo
git clone --depth 1 https://github.com/galimar/veridge

Made for: Codex, OpenCode.

Per session 511 This file is loaded in full into every session.
When invoked 511 The same file — it is already loaded in full.
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 $0.00511 $0.00511
Opus 5 $0.00255 $0.00255
Sonnet 5 $0.00102 $0.00102
Haiku 4.5 $0.00051 $0.00051

Measured yesterday against content hash 366dc449dc8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

veridge 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.

AGENTS.md · 41 lines

What it actually says

AGENTS.md — working on Veridge

Veridge builds an always-fresh, low-token graph of a whole project (files + symbols + areas + decisions + git sessions), ranks it with PageRank, and serves token-budgeted slices to AI assistants and humans. The core has zero runtime dependencies (Python standard library only).

Setup & checks

pip install -e ".[dev,mcp,treesitter]"
ruff check veridge tests      # must pass
pytest -q                     # must pass

Every change must keep ruff and pytest green, and add/adjust tests for behaviour changes.

Design principles (do not break)

read-only on the user's sources · zero-deps core (any new dependency goes behind an optional extra, never in the core) · low-token (queries return structure, never file contents) · ranked (relevance from the graph, not raw counts) · deterministic (nodes and edges are sorted on serialization → reproducible graph.json). No LLM builds the graph.

Layout

  • model.py — typed nodes/edges + indexed adjacency (O(degree) queries)
  • walk.py / ignore.py / classify.py — file enumeration and typing
  • parse_python.py (stdlib ast) + treesitter.py (optional extra) — symbols, imports, calls
  • parse_docs.py — references (links / wikilinks / prose paths) + decision ids
  • indexer.py — assembles the graph; sessions.py — git history
  • rank.py (PageRank) · budget.py (token cost) · query.py (map / find / neighbors / focus / impact / tour / why)
  • freshness.py (manifest + anti-drift gate) · store.py (.veridge/) · watch.py · export.py · integrate.py
  • viewer.py + ui/template.html — offline canvas graph · cli.py · mcp_server.py

More

README.md (usage), ROADMAP.md (plan & what's intentionally out of scope), CONTRIBUTING.md (PR guidance), docs/graph-format.md (the graph.json schema).

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 · 41 lines · 511 tokens per session scan A 366dc449dc8e

Subscribe to this mod's changes

veridge AGENTS.md is an instructions file published in the GitHub repository galimar/veridge (1 stars, last pushed 2mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 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.

Data and AILLMResearchTestingai-agentscode-graphdeveloper-toolsknowledge-graphmcp
Related

Other instructions, from other repositories

CodeStory AGENTS.md

Instructions for TheGreenCedar/CodeStory, covering codestory agent guide, start here, ownership boundaries, product invariants and identity and configuration.

TheGreenCedar/CodeStory · 5,498 tokens

CodeStory copilot-instructions.md

Instructions for TheGreenCedar/CodeStory: Use CodeStory proactively for repository questions. Do not wait for the user to mention it by name.

TheGreenCedar/CodeStory · 139 tokens

kivgraph AGENTS.md

Instructions for Luqueee/kivgraph, covering instrucciones de desarrollo de kivgraph, mapa de instrucciones, identidad del proyecto, qué pregunta contesta cada tool de kivgraph and la puerta delante de grep.

Luqueee/kivgraph · 9,652 tokens

EngramGraph AGENTS.md

Instructions for AsiaOstrich/EngramGraph, covering agents.md, build & test, code style, git workflow and testing.

AsiaOstrich/EngramGraph · 1,144 tokens

aSPARK-graph CLAUDE.md

Instructions for a-lottes/aSPARK-graph, covering claude.md — aspark-graph, what this is, layout & the one load-bearing convention, non-negotiables (each retired a real risk — don't regress) and using aspark-graph in /peer-review (this repo).

a-lottes/aSPARK-graph · 3,474 tokens

kivgraph CLAUDE.md

Instructions for Luqueee/kivgraph, a project described as: A local MCP server for cross-repository semantic code intelligence in TypeScript and Go, backed by a persistent LadybugDB graph.

Luqueee/kivgraph · 3 tokens