issue-tracker

A repository-specific issue tracker that stores work items as YAML files in the .4x/features folder and manages them through the 4x command-line tool. It is separate from GitHub Issues, though settings may link items to GitHub or GitLab issues.

In plain words
What is it for?
Use it to create, list, inspect, and update features and subtasks. It helps track pipeline stages, dependencies, priorities, review status, and links to external issue trackers when configured.
Why use it?
It gives the project one defined place and process for recording feature work, dependencies, priorities, and progress. This prevents agents from assuming that GitHub Issues are the source of truth.

Agent

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 agents/ggwhite/4x/issue-tracker
Clone the repo
git clone --depth 1 https://github.com/ggwhite/4x
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 573 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 $0.00000 $0.00573
Opus 5 $0.00000 $0.00287
Sonnet 5 $0.00000 $0.00115
Haiku 4.5 $0.00000 $0.00057

Measured 2d ago against content hash 103e16451b9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-tracker 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.

docs/agents/issue-tracker.md · 36 lines

What it actually says

Issue tracker: 4x feature system (this repo's own tracker)

Issues/tickets for this repo are tracked as 4x feature YAML files under .4x/features/{feature-id}.yaml, managed via the 4x CLI — not GitHub Issues. (.4x/settings.json's issue_tracker.enabled can additionally link a feature to a GitHub/GitLab issue when configured — check settings before assuming plain local-only.)

Conventions

  • Create: 4x new "<name>" --desc "..." [--subtask "id:name"]... [--rule "..."]... [--depends F0xx]... [--priority N] [--id <slug>]. Follow CLAUDE.md's Feature Description 撰寫規則 (現狀/需求/約束/subtasks) for the --desc body.
  • Read: cat .4x/features/{feature-id}.yaml, or 4x status {feature-id} for current pipeline state (phase/round, not just the YAML's static status).
  • List: 4x status (all features) or ls .4x/features/.
  • Update: edit the YAML directly, respecting the role write-boundaries in CLAUDE.md (e.g. only Designer touches repos; humans/orchestrator own top-level metadata like priority/rules/depends).
  • "Labels" / triage state: the status field — one of draft, not-started, in-progress, ready-for-review, blocked, needs-attention, done, abandoned.
  • Dependencies / blocking: the feature's own depends: [F0xx, ...] array — no separate dependency graph API.
  • Close: features reach done/abandoned through the pipeline (4x done, 4x force-done, or the Acceptor role) — not by hand-editing status.
  • Comment / discussion: no first-class comment thread. Use docs/reference/discovered-feature-gaps.md for non-blocking notes spotted mid-task, or the feature's .4x/run/{feature-id}/ artifacts for pipeline-produced findings.

When a skill says "publish to the issue tracker"

Run 4x new with a --desc that follows the 現狀/需求/約束/subtasks structure.

When a skill says "fetch the relevant ticket"

Read .4x/features/{feature-id}.yaml directly, or run 4x status {feature-id}.

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 · 36 lines · 0 tokens per session scan A 103e16451b9b

Subscribe to this mod's changes

issue-tracker is an agent published in the GitHub repository ggwhite/4x (33 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 573 tokens. 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.