traverse AGENTS.md

A coordination guide for developers and AI agents working on Traverse, a software framework. It defines checks for whether a GitHub issue is already claimed before an agent starts work.

In plain words
What is it for?
Claiming Traverse GitHub issues safely and checking for conflicting Claude Code ownership or branches.
Why use it?
It reduces the risk of two agents changing the same issue at once. The checks identify existing ownership labels and branches before code is modified.

Instructions file for CodexOpenCode

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/traverse-framework/traverse/agents-md
Clone the repo
git clone --depth 1 https://github.com/traverse-framework/traverse

Made for: Codex, OpenCode.

Per session 565 This file is loaded in full into every session.
When invoked 565 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 $0.00565 $0.00565
Opus 5 $0.00282 $0.00282
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00056 $0.00056

Measured 2d ago against content hash dc7144767d0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

traverse 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Traverse — Agent Coordination

Canonical agent instructions (scope, structure, commands, style, governance) live in CLAUDE.md. This file holds only multi-tool coordination, per the org rule in traverse-framework/.github docs/ai-agent-hardening.md: claim before you code — one issue = one agent.

Agent Coordination

Before starting any work on an issue, run these pre-flight checks:

1. Check for Claude Code claim

gh issue view <NUMBER> --repo traverse-framework/traverse --json labels

If the labels include agent:claudeSTOP. Report:

Issue #<NUMBER> is claimed by Claude Code. Choose a different ticket.

2. Check for Claude Code branch

git ls-remote --heads origin | grep "issue-<NUMBER>-"

If a claude/issue-<NUMBER>-* branch exists → STOP. Report:

A Claude Code branch already exists for issue #<NUMBER>. Choose a different ticket.

3. Claim the ticket (only if pre-flight passes)

# Add label (the ownership marker — the live org Project 1 has no Agent field)
gh issue edit <NUMBER> --repo traverse-framework/traverse --add-label "agent:codex"

# Get project item ID with bounded output
gh project item-list 1 --owner traverse-framework --format json --limit 300 \
  --jq '.items[] | select(.content.number == <NUMBER>) | .id'

# Set Status → In Progress
gh project item-edit --project-id PVT_kwDOEbiBt84Bbyp1 \
  --id <ITEM_ID> \
  --field-id PVTSSF_lADOEbiBt84Bbyp1zhWglqM \
  --single-select-option-id 47fc9ee4

Status option IDs for reference: Ready f75ad846, In Progress 47fc9ee4, Done 98236657, Blocked 294b89f5.

Active Technologies

  • Rust 1.94+; host packages in TypeScript, Swift, Kotlin, and .NET + Cargo workspace, serde, semver, existing registry and embedder packages (524-production-app-readiness)
  • host-owned verified artifact cache, append-only trace journal, host-owned file-backed DataStore v2 (524-production-app-readiness)

Recent Changes

  • 524-production-app-readiness: Added Rust 1.94+; host packages in TypeScript, Swift, Kotlin, and .NET + Cargo workspace, serde, semver, existing registry and embedder packages

Read the full file on GitHub · 52 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 · 52 lines · 565 tokens per session scan A dc7144767d0c

Subscribe to this mod's changes

traverse AGENTS.md is an instructions file published in the GitHub repository traverse-framework/traverse (93 stars, last pushed 2d ago), licensed Apache-2.0. It adds 565 tokens to every session, about $0.0028 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.