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.
npx agentmods add agents/ggwhite/4x/issue-trackergit clone --depth 1 https://github.com/ggwhite/4xWhat 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.
| Model | Per session | Once 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 |
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.
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--descbody. - Read:
cat .4x/features/{feature-id}.yaml, or4x status {feature-id}for current pipeline state (phase/round, not just the YAML's staticstatus). - List:
4x status(all features) orls .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 likepriority/rules/depends). - "Labels" / triage state: the
statusfield — one ofdraft,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/abandonedthrough the pipeline (4x done,4x force-done, or the Acceptor role) — not by hand-editingstatus. - Comment / discussion: no first-class comment thread. Use
docs/reference/discovered-feature-gaps.mdfor 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}.
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.
- 2d ago First seen · 36 lines · 0 tokens per session scan A 103e16451b9b
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.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…