Borrowing it
Nothing to install: this file belongs to vitas/evidra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vitas/evidra/main/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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/vitas/evidra/claude-md"><img src="https://agentmods.dev/badge/instructions/vitas/evidra/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02131 | $0.02131 |
| Opus 5.5 | $0.00852 | $0.00852 |
| Sonnet 5.5 | $0.00426 | $0.00426 |
| Haiku 4.5 | $0.00213 | $0.00213 |
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 1mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for agents working in this repository. More specific instructions (the user, the plan) take precedence.
Evidra Core is an MCP execution-evidence recorder, not a scoring platform. One endpoint wraps one upstream MCP server, merges two local tools into its tool list, enforces protocol order, and writes a signed evidence chain that a human reconciles afterwards.
Read before changing behaviour:
docs/architecture.md defines the runtime boundaries;
docs/evidence-format.md defines the event and trust model;
docs/validation.md records what has and has not been measured;
docs/getting-started.md and
docs/cli-reference.md are what a user reads. The approved
design and implementation plan for active work live under docs/plans/.
Build & Test
make build # bin/evidra, bin/evidra-mcp
make test # canonical repository test target
go test ./cmd/... ./pkg/... -v -count=1 # equivalent direct Core scope
make fmt lint tidy
go build -o bin/evidra-fixture ./cmd/evidra-fixture/ # conformance upstream
go build -o bin/evidra-gatea ./cmd/evidra-gatea/ # experiment runner
go test -race ./pkg/evidence/... ./pkg/proxy/... ./pkg/report/... ./cmd/evidra-fixture/... ./cmd/evidra-gatea/...
golangci-lint run ./... # must report zero issues
bash tests/run_guards.sh # every shell guard, no exclusion list
CI references are themselves checked: tests/test_ci_workflows_resolve.sh fails if a live
workflow names a make target, script, package path, config or -run pattern that does not
exist, and tests/core-workflows.txt declares every workflow as enabled or disabled
(a disabled workflow must carry its refusal marker). The package graph is an exact declared
set in tests/core-packages.txt, not a count floor.
Single case: go test -run 'TestName' -v ./pkg/proxy/. Gate artifacts cite tests by name, so
renaming or deleting one means updating the artifact in the same commit — a checklist row
pointing at a function that no longer compiles is not evidence of anything.
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.
- 1mo ago Changed · -62 tokens per session 0b04f199156a
- 1mo ago Changed · -23 lines · +128 tokens per session 5690f3386d46
- 2mo 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 2,131 tokens to every session, about $0.0085 per session on Opus 5.5. 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.
evidra CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| evidra CLAUDE.mdvitas/evidra | Instructions file | 15 | 1mo ago | Apache-2.0 | A | 2,131 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |