Borrowing it
Nothing to install: this file belongs to piyushpathakqa/Vigilis. 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/piyushpathakqa/Vigilis/main/CLAUDE.mdgit clone --depth 1 https://github.com/piyushpathakqa/VigilisWrote 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/piyushpathakqa/vigilis/claude-md)<a href="https://agentmods.dev/instructions/piyushpathakqa/vigilis/claude-md"><img src="https://agentmods.dev/badge/instructions/piyushpathakqa/vigilis/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 5.1 | $0.01621 | $0.01621 |
| Opus 5 | $0.00811 | $0.00811 |
| Sonnet 5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
Vigilis 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 7d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vigilis — Product & Engineering Context
Context for an AI coding agent (Claude Code) working in this repository. Companion to
AGENTS.md(which covers implementation status, milestones, and repo layout). This file covers product thesis, principles, and architecture constraints — read both.
1. What Vigilis is
Vigilis is a trust and provenance layer for autonomous testing — not "another self-healing test tool."
The thesis: an agent rewrites tests autonomously, so the only question that matters is "can I trust what it did?" Vigilis answers that with verifiable, signed proof of every tool call and model decision. Self-healing is the wedge (it earns adoption); attestation is the product (it's the defensible value).
One-line positioning: the trust layer for autonomous testing — works with the test healer you already have.
2. Core principles that must hold in the code
- Attestation is the product; healing is the wedge. Do not invest in healing as the differentiator — framework-native healers (e.g. Playwright agents) are commoditizing it. Invest in making every agent action verifiable.
- The attestation backend must be swappable. Treeship is the current implementation but must sit behind an interface (e.g.
AttestationProvider). Never hard-couple to it. A local/no-op provider must exist so the system runs and tests pass without Treeship. This is non-negotiable: a customer deployment must not break if Treeship is unavailable. - Never mask a real bug. This is enforced behavior, not a comment. The heal path must distinguish dom-drift (safe to heal) from genuine behavior change (must fail and surface). When triage is uncertain, fail loudly rather than heal. The triage decision and its rationale must be captured in the attestation record so it is auditable.
- Agent-agnostic. Where possible, sit on top of execution/healing agents and attest their actions rather than reinventing the healer. The long-term target is attesting any engineering agent, not just Vigilis's own.
- Clean open-core boundary. Keep the agent/healing/attestation-client core OSS-clean. The commercial layer (org policy/governance, audit reporting, dashboards, SSO, multi-tenant) is separate. The OSS core must not depend on the paid layer; the paid layer must not leak proprietary logic into the core.
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.
- 7d ago First seen · 93 lines · 1,621 tokens per session scan A 3531fda5a6e6
Vigilis CLAUDE.md is an instructions file published in the GitHub repository piyushpathakqa/Vigilis (5 stars, last pushed 18d ago), licensed MIT. It adds 1,621 tokens to every session, about $0.0081 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.