regressGuard CLAUDE.md

Repository instructions for RegressGuard, a Go command-line tool and MCP server that compares an API against a known-good baseline to detect regressions.

In plain words
What is it for?
Use them when modifying RegressGuard, especially its baseline checks, commit blocking, MCP connection, user experience, tests, and documentation.
Why use it?
They tell contributors what to read first, how to judge changes, and which reliability and security issues matter most.

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/bharath-code/regressguard/claude-md
Clone the repo
git clone --depth 1 https://github.com/Bharath-code/regressGuard
Per session 784 This file is loaded in full into every session.
When invoked 784 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 $0.00784 $0.00784
Opus 5 $0.00392 $0.00392
Sonnet 5 $0.00157 $0.00157
Haiku 4.5 $0.00078 $0.00078

Measured 2d ago against content hash 116b4220fca0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

regressGuard 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 2d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — RegressGuard

One-line: a single-binary Go CLI that records a known-good API baseline and blocks commits when an AI agent silently regresses it. Also an MCP server so the agent can verify its own work.

Read first

  • AGENTS.md — workflow, tech stack, project structure, CLI/UX/error/test conventions.
  • RegressGuard-PRD.md Section 11 — implementation source of truth (task tracker).
  • docs/staff-review-2026-06.md — current product review, verdict, and prioritized task breakdown with acceptance criteria.

AGENTS.md rules apply in full; this file does not restate them. On conflict, the PRD and AGENTS.md win.

Product verdict (2026-06-15): PURSUE (conditional)

Real, well-evidenced problem; high build quality; unique wedge = agent-native verification via MCP. Gated on three conditions before growth spend:

  1. Eliminate transient-error false positives (trust is the whole product).
  2. Calm-by-default UX (animations opt-in, instant default).
  3. Harden + test the MCP path; make the open-core/monetization story real.

Current priorities (see docs/staff-review-2026-06.md for acceptance criteria)

  • ✅ Done: P0 transient-error FP, P0 secret hygiene (verified), P1-2 MCP hardening + tests, P1-1 calm-by-default UX (animations opt-in via --celebrate), P1-3 scoring-semantics docs
    • warning-only routes excluded from "unchanged" count, P2-1 open-core positioning + docs/json-contract.md + docs/paid-layer-spec.md.
  • P2-2 (spec only, per AGENTS.md scope) — FastAPI/Django route-discovery spec for scanner, gated behind PRD change-control before any code.

Architecture quick map

  • internal/engine — test runner, route hitter, schema normalizer, diff (severity rules).
  • internal/checkrunrg check pipeline (load snapshot, rerun, diff, render).
  • internal/snapshot — baseline read/write + HMAC integrity + field redaction.
  • internal/mcprun — exposes snapshot/check/status as MCP tools (strategic differentiator).
  • internal/ui — design system; all color via ui.Paint(), animations TTY-only.

Read the full file on GitHub · 55 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. 2d ago First seen · 55 lines · 784 tokens per session scan A 116b4220fca0

Subscribe to this mod's changes

regressGuard CLAUDE.md is an instructions file published in the GitHub repository Bharath-code/regressGuard (1 stars, last pushed 1mo ago), licensed MIT. It adds 784 tokens to every session, about $0.0039 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.

Related

Other instructions, from other repositories

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).

microsoft/vscode · 6,785 tokens

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.

github/spec-kit · 7,104 tokens

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.

openai/codex · 5,182 tokens

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.

langchain-ai/langchain · 4,345 tokens

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).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens