tactual copilot-instructions.md

Project instructions for Tactual, a TypeScript tool with a library, command-line program, MCP server, browser-testing support, and GitHub Action.

In plain words
What is it for?
Changing Tactual’s command-line, library, MCP, browser-testing, reporting, GitHub Action, or deployment-related surfaces while preserving matching behavior.
Why use it?
They require changes to stay consistent across all public ways people use the project and point to the relevant tests and configuration files.

Instructions file for GitHub Copilot

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/tactual-dev/tactual/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/tactual-dev/tactual

Made for: GitHub Copilot.

Per session 903 This file is loaded in full into every session.
When invoked 903 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 $0.00903 $0.00903
Opus 5 $0.00451 $0.00451
Sonnet 5 $0.00181 $0.00181
Haiku 4.5 $0.00090 $0.00090

Measured 2d ago against content hash 2aeab2bd7bbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tactual copilot-instructions.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.

.github/copilot-instructions.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — Tactual

Surface Parity Mandate (REQUIRED)

Tactual is a single-package TypeScript repo with several public surfaces:

  • Library exports: tactual, tactual/playwright, tactual/mcp, tactual/validation, tactual/calibration
  • CLI: tactual
  • MCP server: tactual-mcp (stdio by default, Streamable HTTP optional)
  • GitHub Action: action.yml
  • Hosted/container metadata: Dockerfile, smithery.yaml, glama.json

Before changing user-visible behavior, check and keep these in sync:

  • src/cli/index.ts
  • src/mcp/index.ts
  • README.md
  • CHANGELOG.md
  • action.yml when the GitHub Action surface is affected
  • Relevant tests (src/cli/cli.test.ts, src/mcp/mcp.test.ts, reporter/playwright tests as appropriate)

If a change affects marketplace or registry metadata, also check package.json, server.json, glama.json, and smithery.yaml.

Architecture Overview

  • src/core/ — shared types, config/filtering, graph building, path analysis, analyzer, finding builder
  • src/playwright/ — page capture, exploration, probes, and safe-action policy
  • src/reporters/ — JSON / Markdown / Console / SARIF output
  • src/mcp/ — MCP tool registration, trace helpers, HTTP transport
  • src/profiles/ — AT profile definitions and registration
  • src/rules/ — rule-based penalties and fix suggestions
  • src/calibration/ and src/benchmark/ — tuning and validation surfaces
  • Tests are mostly colocated as *.test.ts

Read ARCHITECTURE.md before larger refactors and README.md before changing user-facing claims or examples.

Output Contract (REQUIRED)

  • json, markdown, and console output are summarized. The summary contract lives in src/reporters/summarize.ts; do not replace it with raw full-result dumps casually.
  • sarif is the concise actionable format for CI/MCP use. src/reporters/sarif.ts intentionally caps results to stay LLM-friendly.
  • Findings carry Playwright-style locator selectors. Do not describe them as CSS selectors unless the representation is intentionally changed across code, docs, and tests.
  • summaryOnly already exists in both CLI and MCP. If you change its shape or behavior, update both surfaces and their docs/tests together.

Read the full file on GitHub · 73 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 · 73 lines · 903 tokens per session scan A 2aeab2bd7bbe

Subscribe to this mod's changes

tactual copilot-instructions.md is an instructions file published in the GitHub repository tactual-dev/tactual (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 903 tokens to every session, about $0.0045 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.