debugg-ai-mcp: Instructions file for Codex

AGENTS.md

debugg-ai-mcp AGENTS.md is an instructions file for Codex, OpenCode from debugg-ai/debugg-ai-mcp. It costs 1,877 tokens per session, scanned B, original, Apache-2.0.

Repository instructions for a debugging MCP server, covering issue tracking, automated checks, and optional testing against its live API.

In plain words
What is it for?
Use them to manage Beads issues, run tests, type checks, linting, builds, and deliberate end-to-end API verification.
Why use it?
They provide the project’s expected workflow and warn when a test can change real data or use a different backend.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is debugg-ai/debugg-ai-mcp's own configuration. It tells Codex and OpenCode how to work on debugg-ai-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything debugg-ai-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to debugg-ai/debugg-ai-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/debugg-ai/debugg-ai-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/debugg-ai/debugg-ai-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for debugg-ai-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/debugg-ai/debugg-ai-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/debugg-ai/debugg-ai-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/debugg-ai/debugg-ai-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/debugg-ai/debugg-ai-mcp/agents-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.

agentmods 80×15 button for debugg-ai-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/debugg-ai/debugg-ai-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/debugg-ai/debugg-ai-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,877 This file is loaded in full into every session.
When invoked 1,877 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01877 $0.01877
Opus 5.5 $0.00751 $0.00751
Sonnet 5.5 $0.00375 $0.00375
Haiku 4.5 $0.00188 $0.00188

Measured 1mo ago against content hash 219d8afc1bf9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

debugg-ai-mcp AGENTS.md scanned grade B 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 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.

Reads MCP configurationmediumAgent snooping

mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.

- The MCP reads **`DEBUGGAI_API_KEY` from the environment** — `.mcp.json` references `${DEBUGGAI_API_KEY}`
Origin

Copies of this mod

2 near-identical copies found in the catalogue:

AGENTS.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

This project uses bd (beads) for issue tracking. Run bd onboard to get started.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --status in_progress  # Claim work
bd close <id>         # Complete work
bd sync               # Sync with git

Testing & live verification

npm test            # unit tests (jest, ESM + ts-jest; use `import { jest } from '@jest/globals'`)
npx tsc --noEmit    # typecheck
npm run lint        # eslint
npm run build       # tsc -> dist/

Unit tests mock the backend. To verify a tool end-to-end against the real API:

  • The MCP reads DEBUGGAI_API_KEY from the environment — .mcp.json references ${DEBUGGAI_API_KEY} (never a literal). Export it first: export DEBUGGAI_API_KEY=<key>.
  • No dev-mode → prod api.debugg.ai. DEBUGGAI_DEV_MODE=true → local backend http://localhost:8012 (needs a local token; the prod key won't auth there).
  • npm run test:integration hits the real API, self-skips without a key, and writes data — be deliberate about which backend you target.
  • Fast read-only smoke of a fresh build (npm run build first) — replicate the CallTool path:
    import { getTool } from './dist/tools/index.js';
    import { validateInput } from './dist/utils/validation.js';
    const t = getTool('project');
    console.log(await t.handler(validateInput(t.inputSchema, { action: 'list' }, 'project'), { timestamp: new Date() }));
    
    Use read-only actions (list/get) on project/environment/executions.

Tunnel mechanics for localhost URLs: check_app_in_browser/probe_page/trigger_crawl auto-tunnel http(s)://localhost:* targets through one tunnel per session key (not per port) dialed at a local Caddy reverse proxy that gets repointed per dispatch under a lock — see docs/local-tunnel-multiplexer-architecture-2026-07-31.md, docs/debugg-tunnel-server-design-2026-09-19.md, and services/tunnel//services/caddy/. The tunnel is the debugg tunnel server (<id>.tunnel.debugg.ai), reached by a pure-TS websocket mux client (services/tunnel/debuggTransport.ts); the ngrok client was removed once that shipped. The caddy binary is still required for any localhost-URL call: it auto-installs via the @radically-straightforward/caddy npm dependency's postinstall (pinned version) — CADDY_BIN overrides it if that download never ran. Fails fast with CaddyBinaryNotFoundError if neither is available. test_suite {action:"run"} is the exception: dedicated per-call tunnel, bypasses Caddy, no caddy needed.

Read the full file on GitHub · 196 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. 1mo ago Changed · +4 lines · +64 tokens per session 219d8afc1bf9
  2. 1mo ago First seen · 192 lines · 1,813 tokens per session scan B deb34430d9bc

Subscribe to this mod's changes

debugg-ai-mcp AGENTS.md is an instructions file published in the GitHub repository debugg-ai/debugg-ai-mcp (68 stars, last pushed 9d ago), licensed Apache-2.0. It adds 1,877 tokens to every session, about $0.0075 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories