evidra CLAUDE.md

evidra CLAUDE.md is an instructions file for coding agents from vitas/evidra. It costs 2,065 tokens per session, scanned A, original, Apache-2.0.

A repository guide for Evidra, a Go-based flight recorder that observes the reliability of infrastructure automation and AI agents.

In plain words
What is it for?
Use it when building, testing, formatting, linting, packaging, or committing changes to Evidra and its command-line, MCP, and API programs.
Why use it?
It puts build, test, formatting, linting, Docker, architecture, and commit requirements in one place, reducing guesswork during development.

Instructions file

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/vitas/evidra/claude-md
Clone the repo
git clone --depth 1 https://github.com/vitas/evidra

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 evidra CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vitas/evidra/claude-md.svg)](https://agentmods.dev/instructions/vitas/evidra/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vitas/evidra/claude-md"><img src="https://agentmods.dev/badge/instructions/vitas/evidra/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,065 This file is loaded in full into every session.
When invoked 2,065 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 $0.02065 $0.02065
Opus 5 $0.01033 $0.01033
Sonnet 5 $0.00413 $0.00413
Haiku 4.5 $0.00206 $0.00206

Measured 4d ago against content hash c9e25ab211b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evidra CLAUDE.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 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.

CLAUDE.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build & Test Commands

make build                              # build bin/evidra, bin/evidra-mcp, bin/evidra-api
make test                               # go test ./... -v -count=1
make fmt                                # gofmt -w .
make lint                               # golangci-lint run
make tidy                               # go mod tidy
make canon-fixtures-update              # regenerate canon golden test files
make docker-mcp                         # build MCP server Docker image
make docker-cli                         # build CLI Docker image
make docker-api                         # build API server Docker image

go test -run TestFunctionName ./internal/canon/...   # run a single test
go test -race ./...                                  # race detector

Git

Alsways ask to push to remote repo Always use Signed-off-by to make a git commits

Architecture

Evidra is a flight recorder for infrastructure automation — it observes and measures AI agent and CI pipeline reliability without blocking operations.

Module: samebits.com/evidra (Go 1.24)

Binaries

  • cmd/evidra/ — CLI for prescribe, report, scorecard, explain, compare, record, import, export, validate, import-findings, prompts, detectors, keygen, skill, and version commands
  • cmd/evidra-mcp/ — MCP server with two modes: direct (agent calls prescribe/report) and proxy (wraps upstream MCP server, auto-records mutations)
  • cmd/evidra-api/ — Self-hosted API server with embedded UI, webhooks, and database-backed storage

Core pipeline

raw artifact → canonicalize (adapter) → CanonicalAction + digests
                                              │
                                    assess.Pipeline [Assessor 1..N]
                                              │
                                    risk_inputs[] + effective_risk → Prescription
                                                                          ↓
exit code + prescription_id → Report → signal detectors → Scorecard

Read the full file on GitHub · 168 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 · 168 lines · 2,065 tokens per session scan A c9e25ab211b2

Subscribe to this mod's changes

evidra CLAUDE.md is an instructions file published in the GitHub repository vitas/evidra (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,065 tokens to every session, about $0.0103 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.