agentmods.dev

Teamwork AGENTS.md

Repository instructions for the Teamwork project covering its skills, working conventions, commands, releases, and project rules. They define how changes should be made and documented in that repository.

In plain words
What is it for?
Guiding changes to skills and policy files, shell-script style, frontmatter checks, release work, documentation scope, and optional agent delegation in the Teamwork repository.
Why use it?
They give coding agents a shared set of rules for keeping workflow behavior, documentation, tests, scripts, and commits consistent.

Instructions file for CodexOpenCode

11 6d ago A scan 614 tokens original MIT
View the source file JinPLu/Teamwork
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/jinplu/teamwork/agents-md
Clone the repo
git clone --depth 1 https://github.com/JinPLu/Teamwork

Made for: Codex, OpenCode.

Per session 614 This file is loaded in full into every session.
When invoked 614 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 $0.00614 $0.00614
Opus 5 $0.00307 $0.00307
Sonnet 5 $0.00123 $0.00123
Haiku 4.5 $0.00061 $0.00061

Measured 2d ago against content hash 8ab7da4aab80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Teamwork AGENTS.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.

AGENTS.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teamwork Repository

skills/ is the source of truth. Clear authorized work stays native; a named Skill adds only the method described by its trigger. Cursor and Claude Code adapters are optional compatibility surfaces and never block Codex work.

Working Conventions

  • Change the owning SKILL.md before workflow behavior. Public docs stay outcome-focused.
  • policy/teamwork-global.md carries cross-project working rules that must hold before any Skill loads, plus the minimum routing, delegation, and persistence bridge. A rule an owning SKILL.md already carries does not belong there, and a test must not require the same sentence in both places. Commit a change to that file separately from the release commit, carrying only the edits needed to keep the tree green, so its growth stays reviewable on its own.
  • Shell scripts use Bash with set -euo pipefail, quoted variables, and arrays; every SKILL.md frontmatter has only name and description, whose value starts with Use when.
  • Agent delegation is optional unless the user explicitly requires independent work. Handoffs contain only objective, scope, settled constraints, evidence, and requested return. Missing agents never trigger Update automatically.
  • Project-local Teamwork setup is one concise managed AGENTS.md block. It has no document database, schema, case lifecycle, or migration gate.

Commands

  • Run ./scripts/validate.sh for the small local smoke suite. Use ./scripts/validate.sh --release only for explicit release preparation.
  • ./scripts/check-update.sh --readiness reports Codex install state without becoming a workflow gate. init-project maintains the project instruction block; update refreshes Codex unless another host is explicitly selected.

Releases

  • Release on main unless the user explicitly requests another Git workflow.
  • VERSION consistency is checked by ./scripts/validate.sh.
  • A release is complete only after the requested verification, commit, tag, and GitHub Release succeed. Cursor/Claude adapters and project-local files are not release blockers.
  • Keep release notes short and describe user-visible behavior rather than internal tests, gates, or version history.

Read the full file on GitHub · 51 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 · 51 lines · 614 tokens per session scan A 8ab7da4aab80

Subscribe to this mod's changes

Teamwork AGENTS.md is an instructions file published in the GitHub repository JinPLu/Teamwork (11 stars, last pushed 6d ago), licensed MIT. It adds 614 tokens to every session, about $0.0031 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 2026-08-30.

Data and AIGit and workflowWriting and docsagent-skillsai-agentsclaude-codecodexcursordeveloper-tools
Related

Other instructions, from other repositories

awesome-copilot-id AGENTS.md

Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.

GulajavaMinistudio/awesome-copilot-id · 7,686 tokens

hiveshare CLAUDE.md

Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.

KB-perByte/hiveshare · 1,301 tokens

llm-safe-haven CLAUDE.md

Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.

pleasedodisturb/llm-safe-haven · 1,322 tokens

kleosrules AGENTS.md

Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).

kleosr/kleosrules · 417 tokens

coding-agent-safety-gate AGENTS.md

Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.

ASER-ho/coding-agent-safety-gate · 589 tokens

yapcap CLAUDE.md

Claude Code instructions for TopiCsarno/yapcap, a project described as: Native COSMIC panel applet showing local usage limits for Codex, Claude Code, and Cursor.

TopiCsarno/yapcap · 3 tokens