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.
npx agentmods add instructions/vitas/evidra/claude-mdgit clone --depth 1 https://github.com/vitas/evidraWrote 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.
[](https://agentmods.dev/instructions/vitas/evidra/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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 commandscmd/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
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.
- 4d ago First seen · 168 lines · 2,065 tokens per session scan A c9e25ab211b2
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.
Other instructions, from other repositories
mobilegym AGENTS.md
Instructions for Purewhiter/mobilegym, covering agents.md, project overview, type-checking strategy, eslint and with data graph generation.
ClawBench AGENTS.md
AGENTS.md instructions for TIGER-AI-Lab/ClawBench, covering clawbench -- agent context, what this is, project structure, setup and 2. configure at least one model.
strix-halo-guide AGENTS.md
AGENTS.md instructions for hogeheer499-commits/strix-halo-guide, covering agents.md, core project lens, documentation style, do-not-invent rules and benchmark claim rules.
flyto-core AGENTS.md
AGENTS.md instructions for flytohub/flyto-core, covering flyto-core agent rules, flyto2 project memory contract, flyto2 frontend quality gate and repo notes.
openbench AGENTS.md
Instructions for minghinmatthewlam/openbench, covering openbench — agent context, local execution context, what openbench is, execution ownership and product goals (the two things we are building toward).
aws-bench AGENTS.md
AGENTS.md instructions for aws-bench/aws-bench, covering agents.md, setup, commands, project structure and code style.