What is httap AGENTS.md?

Project instructions for httap, a terminal tool that captures and displays web traffic through a proxy. A proxy is an intermediary that can inspect requests between an application and the internet.

Use them when developing or maintaining httap, especially its terminal interface, per-project traffic data, mock generation, and AI integration.

They explain the project's priorities, current work source, review-file location, and design principles so changes stay consistent with the tool's intended workflow.

httap AGENTS.md — Instructions file by mtford90

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/mtford90/httap/agents-md

Clone the repo

git clone --depth 1 https://github.com/mtford90/httap

Made for: Codex, OpenCode.

Per session 3,080 This file is loaded in full into every session.

When invoked 3,080 The same file — it is already loaded in full.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5	$0.03080	$0.03080
Opus 5	$0.01540	$0.01540
Sonnet 5	$0.00616	$0.00616
Haiku 4.5	$0.00308	$0.00308

Measured 2d ago against content hash 7a9d0a905ebb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

httap AGENTS.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Examples**: `src/daemon/storage.test.ts`, `src/cli/tui/utils/curl.test.ts`, `src/daemon/proxy.test.ts`

AGENTS.md · 261 lines

How it starts

The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

httap - Terminal HTTP Interception Toolkit

Planning & Status

docs/PLAN.md is the source of truth for all development work on this project.

Always check docs/PLAN.md before starting work to understand current priorities
Update docs/PLAN.md when completing tasks (move to Completed section)
Update docs/PLAN.md when discovering new tasks or requirements
Keep task descriptions concise but informative
Code reviews are stored in docs/reviews/<date>/

Published to npm as httap (v0.1.0). The name httap was taken.

Project Overview

httap is a terminal-based HTTP interception/inspection tool with project-scoped isolation and a lazygit-style TUI. It captures HTTP/HTTPS traffic through a MITM proxy and displays it in an interactive terminal interface.

Product Vision

Messaging Pillars

These define what httap is and how it should feel — keep them in mind when making design and UX decisions:

Workspace-isolated — per-project .httap/ directory, no cross-project bleed
Lives in your terminal — TUI, not another GUI app; fits your existing workflow
AI-native — MCP integration, AI writes your mocks, inspects your traffic
Config-as-code — mocks and interceptors are TypeScript files, not GUI toggles
Zero-config — httap on and go; auto-starts daemon, auto-generates certs
Developer-first — built for how you already work, not bolted on

Strategic Direction

The long-term vision centres on mocks & interceptors as code — TypeScript config files inside .httap/ that define middleware/intercept/mock behaviour, with full programmatic access to the httap client. The TUI visualises what's configured, but logic lives in code.

MCP integration is a first-class concern: AI agents should be able to discover .httap, communicate with the proxy, search through captured traffic, and write/manage mock rules via the config-as-code system.

CLI Design Philosophy — Gradual Discovery

The CLI follows a gradual discovery pattern — each command's output hints at what you can do next, so usage builds on itself naturally:

Read the full file on GitHub · 261 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.

2d ago First seen · 261 lines · 3,080 tokens per session scan A 7a9d0a905ebb

Subscribe to this mod's changes

httap AGENTS.md is an instructions file published in the GitHub repository mtford90/httap (8 stars, last pushed 6mo ago), licensed MIT. It adds 3,080 tokens to every session, about $0.0154 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Planning

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

httap AGENTS.md