traverse-ops

A workflow for coordinating development work across tickets, pull requests, and a project board. It tells the agent how to inspect existing work, claim ready tasks, implement changes on dedicated branches, and finish pull requests.

In plain words
What is it for?
Use it to start or resume Traverse development operations, process ready Project 1 issues, finish open pull requests, or run the ready-ticket worker, PR finisher, or backlog gardener.
Why use it?
It provides a repeatable process for keeping ticket status, branches, reviews, and project-board state aligned. This reduces the chance of duplicate work or unfinished changes being overlooked.

Skill for Claude CodeCodex

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 skills/traverse-framework/traverse/traverse-ops
Any agent
npx skills add traverse-framework/traverse --skill traverse-ops
Clone the repo
git clone --depth 1 https://github.com/traverse-framework/traverse

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,502 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00063 $0.01502
Opus 5 $0.00032 $0.00751
Sonnet 5 $0.00013 $0.00300
Haiku 4.5 $0.00006 $0.00150

Measured 2d ago against content hash 1e50d7cf7efe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

traverse-ops 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/skills/traverse-ops/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Traverse Ops

Use this skill when the user wants Codex to start or resume the standard Traverse operating model.

Canonical trigger:

TRAVERSE OPS

Workflow

  1. Read AGENTS.md and follow the agent coordination rules.
  2. Read the constitution (via traverse-framework/.github, pinned in .governance-version) only when the ticket touches architecture, contracts, or versioned surfaces — lazy-read map in the org's docs/ai-agent-hardening.md.
  3. Inspect current GitHub and Project 1 state.
  4. Prefer finishing existing open PRs before claiming new Ready work.
  5. Keep cycling through open PRs and Ready Project 1 issues until no actionable Ready tickets remain. Do not stop after one PR, one issue, or one merge.
  6. If no active PR needs attention, pick the next Ready Project 1 issue.
  7. Before work on an issue, run the Claude pre-flight checks from AGENTS.md:
    • issue must not have agent:claude
    • no remote claude/issue-NNN-* branch may exist
  8. If pre-flight passes, claim the issue:
    • add agent:codex
    • set Project 1 Status to In Progress
  9. Use a dedicated codex/issue-NNN-* branch.
  10. Keep work scoped to the claimed issue and governing spec.
  11. Open a dedicated PR using the org body superset (## Summary, ## Governing Spec, ## Project Item, ## Definition of Done, ## Validation) with validation evidence, then immediately queue it: gh pr merge <N> --squash --auto. Do not poll checks — continue the loop and release on a later pass once merged. This repo requires branches up to date with main (strict checks): rebase when behind, or auto-merge cannot fire.
  12. The stop condition is strict: no mergeable or fixable open PRs, no Ready Project 1 tickets that pass pre-flight, no uncompleted agent:codex tickets, and only explicitly blocked work remains. If a Ready ticket is blocked, update its ticket/Project state with the concrete blocker before continuing to the next Ready ticket.

Continuation Rule (mandatory)

Read the full file on GitHub · 122 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 · 122 lines · 63 tokens per session scan A 1e50d7cf7efe

Subscribe to this mod's changes

traverse-ops is a skill published in the GitHub repository traverse-framework/traverse (93 stars, last pushed 2d ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,502 once invoked, about $0.0003 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.