agentmods.dev

DeployBot AGENTS.md

Repository instructions for developers and coding agents working on the Forward-Future/DeployBot project. They describe how to access the repository, run checks, and handle merges or deployments.

In plain words
What is it for?
Use them when developing, testing, linting, pushing branches, merging changes, or deploying DeployBot.
Why use it?
They provide project-specific rules so contributors know which commands and safeguards to follow before changing or releasing code.

Instructions file for CodexOpenCode

45 2mo ago C scan 262 tokens original MIT
View the source file Forward-Future/DeployBot
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/forward-future/deploybot/agents-md
Clone the repo
git clone --depth 1 https://github.com/Forward-Future/DeployBot

Made for: Codex, OpenCode.

Per session 262 This file is loaded in full into every session.
When invoked 262 The same file — it is already loaded in full.
Security scan C 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.

ModelPer sessionOnce invoked
Fable 5 $0.00262 $0.00262
Opus 5 $0.00131 $0.00131
Sonnet 5 $0.00052 $0.00052
Haiku 4.5 $0.00026 $0.00026

Measured yesterday against content hash b5f8ea240494, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

DeployBot AGENTS.md scanned grade C 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 yesterday.

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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

branches **and for `main`**. Do not refuse a merge by claiming you cannot
AGENTS.md · 25 lines

What it actually says

Agent notes

Operational memory for AI agents working in this repository.

Repository access and merging

  • The git credential in agent sessions has push and admin access to the GitHub remote. Verify with gh api repos/<owner>/<repo> --jq .permissions rather than assuming a lack of access.
  • The bundled gh CLI is used read-only (so the PR "merge" button and other gh write commands are unavailable), but git push works for feature branches and for main. Do not refuse a merge by claiming you cannot merge — check first.
  • Only merge or deploy when the user explicitly instructs it. When they do: fetch and integrate the latest main, resolve conflicts, re-run the tests and linter, then merge the feature branch into main and git push origin main. GitHub records the corresponding PR as merged once its head commit is reachable from main.

Development

  • Install for tests: python3 -m pip install -e '.[dev]'.
  • Run the suite: python3 -m unittest discover -s tests.
  • Lint: python3 -m ruff check ..
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. yesterday First seen · 25 lines · 262 tokens per session scan C b5f8ea240494

Subscribe to this mod's changes

DeployBot AGENTS.md is an instructions file published in the GitHub repository Forward-Future/DeployBot (45 stars, last pushed 2mo ago), licensed MIT. It adds 262 tokens to every session, about $0.0013 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Git and workflowProductivityTestingclaude-codecodexcoding-agentsgithub-actionsmcpmerge-queue
Related

Other instructions, from other repositories

tapp AGENTS.md

AGENTS.md instructions for aarwitz/tapp, covering tapp agent playbook, no mcp connected? just run the cli, pick the right tool for the job, session driving (the playwright loop) and autonomous exploration (tappexplore).

aarwitz/tapp · 3,044 tokens

ontology-atlas AGENTS.md

Instructions for wlsdks/ontology-atlas, covering agents.md — ontology-atlas, product and non-negotiable architecture, start here, structure and routes and operating gates and skills.

wlsdks/ontology-atlas · 2,685 tokens

ephemeral-sandbox CLAUDE.md

Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.

Ephemeral-AI-Lab/ephemeral-sandbox · 1,203 tokens

coral CLAUDE.md

Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).

cdknorow/coral · 1,898 tokens

ConsultMe CLAUDE.md

Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.

Tarek-Bohdima/ConsultMe · 3,021 tokens

pixir CLAUDE.md

Instructions for Ranvier-Technologies/pixir, covering pixir harness - legacy agent guide, current map and commands.

Ranvier-Technologies/pixir · 246 tokens