agentmods.dev

writ

A Claude Code workflow plugin that supplies task-specific rules and controls how an agent plans, tests, and writes code. It uses a knowledge graph, a connected store of related information, to retrieve relevant rules.

In plain words
What is it for?
Use it to apply coding rules, retrieve relevant guidance, enforce test-driven development (writing tests before implementation), and manage coding sessions.
Why use it?
It reduces risky or poorly checked changes by requiring approval of a plan and tests before certain writes.

Plugin for Claude Code

189 17d ago A scan tokens not measured original MIT
View the source file infinri/Writ
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 plugins/infinri/writ/marketplace
Claude Code
/plugin marketplace add infinri/Writ
Clone the repo
git clone --depth 1 https://github.com/infinri/Writ

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

writ 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.

.claude-plugin/marketplace.json · 27 lines

What it actually says

{
  "name": "writ",
  "owner": {
    "name": "Lucio Saldivar"
  },
  "metadata": {
    "description": "Single-plugin marketplace for Writ. The repository root is the plugin, so `source` is './'.",
    "version": "1.7.0"
  },
  "plugins": [
    {
      "name": "writ",
      "source": "./",
      "version": "1.7.0",
      "displayName": "Writ",
      "description": "Guardrails for Claude Code: the rules that fit the task delivered per prompt, and no risky writes before you approve a plan and tests. Hybrid retrieval (BM25 + vector + graph traversal + weighted ranking, with an abstention gate) over a Neo4j knowledge graph, wired in through hook scripts and a session state machine.",
      "category": "workflow",
      "keywords": ["claude-code", "rag", "rules", "enforcement", "neo4j", "fastapi", "hooks", "workflow", "code-quality", "ai-tooling", "governance", "guardrails", "knowledge-graph", "tdd"],
      "homepage": "https://github.com/infinri/Writ",
      "license": "MIT",
      "author": {
        "name": "Lucio Saldivar"
      }
    }
  ]
}
Files

What ships with it

1 file beside marketplace.json 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 · 27 lines scan A d7b199c875c4

Subscribe to this mod's changes

writ is a plugin published in the GitHub repository infinri/Writ (189 stars, last pushed 17d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.

ResearchTestingWriting and docsagent-toolsai-codingclaude-codeknowledge-graphpythonrule-enforcement
Related

Other plugins, from other repositories

hermes-tweet

Hermes Agent plugin for Twitter search, monitoring, follower exports & approved X actions. Not affiliated with X Corp.

Xquik-dev/hermes-tweet · not measured

geckovision

GeckoVision's plugins for making any API agent-usable — comprehension, x402 payments, and anti-poisoning defense.

GeckoVision/gecko-surf · not measured

agent-plus-meta

The meta plugin for the agent-plus framework. Workspace bootstrap, env-var readiness, identity cache, marketplace lifecycle (install/list/update/remove/search/prefer), extensions. One call to init creates .agent-plus/; envcheck reports which sibling-plugin env vars are set (names only); refresh resolves project.

osouthgate/agent-plus · not measured

diff-summary

One-call structured triage of a git diff — file-by-file role classification (source/test/config/doc/generated/build/fixture/migration), risk tier (low/medium/high) with reasons, public-API touch detection, co-changed-test detection, secret-risk path flagging, and aggregate stats. Replaces the 5–20 Read calls an agent…

osouthgate/agent-plus · not measured

skill-feedback

Local-first agent self-assessment for Claude Code skills. After using a skill, the agent appends a structured rating + friction note to /.agent-plus/skill-feedback/ .jsonl. Skill authors aggregate locally with report, or bundle entries into a GitHub issue body for the skill's source repo with submit. No SaaS.

osouthgate/agent-plus · not measured

agent-plus

Plugin marketplace listing 5 plugins: agent-plus-meta, repo-analyze, diff-summary, skill-feedback, skill-plus.

osouthgate/agent-plus · not measured