← 返回
未分类 Key 中文

Disinto Factory

Operate the disinto autonomous code factory. Use when managing factory agents, filing issues on the forge, reading agent journals, querying CI pipelines, che...
Operate the disinto autonomous code factory. Use when managing factory agents, filing issues on the forge, reading agent journals, querying CI pipelines, che...
johba37 johba37 来源
未分类 clawhub v0.1.1 1 版本 100000 Key: 需要
★ 0
Stars
📥 324
下载
💾 0
安装
1
版本
#automation#ci#devops#factory#latest#solo-founder

概述

Disinto Factory Skill

Disinto is an autonomous code factory with nine agents that implement issues,

review PRs, plan from a vision, predict risks, groom the backlog, gate

actions, and assist the founder — all driven by cron and Claude.

Required environment

VariablePurpose
-------------------
FORGE_TOKENForgejo/Gitea API token with repo scope
FORGE_APIBase API URL, e.g. https://forge.example/api/v1/repos/owner/repo
PROJECT_REPO_ROOTAbsolute path to the checked-out disinto repository

Optional:

VariablePurpose
-------------------
WOODPECKER_SERVERWoodpecker CI base URL (for pipeline queries)
WOODPECKER_TOKENWoodpecker API bearer token
WOODPECKER_REPO_IDNumeric repo ID in Woodpecker

The nine agents

AgentRoleRuns via
-----------------------
DevPicks backlog issues, implements in worktrees, opens PRsdev/dev-poll.sh (cron)
ReviewReviews PRs against conventions, approves or requests changesreview/review-poll.sh (cron)
GardenerGrooms backlog: dedup, quality gates, dust bundling, stale cleanupgardener/gardener-run.sh (cron 0,6,12,18 UTC)
PlannerTracks vision progress, maintains prerequisite tree, files constraint issuesplanner/planner-run.sh (cron daily 07:00 UTC)
PredictorChallenges claims, detects structural risks, files predictionspredictor/predictor-run.sh (cron daily 06:00 UTC)
SupervisorMonitors health (RAM, disk, CI, agents), auto-fixes, escalatessupervisor/supervisor-run.sh (cron */20)
ActionExecutes operational tasks dispatched by planner via formulasaction/action-poll.sh (cron)
VaultGates dangerous actions, manages resource procurementvault/vault-poll.sh (cron)
ExecInteractive executive assistant reachable via Matrixexec/exec-session.sh

How agents interact

Planner ──creates-issues──▶ Backlog ◀──grooms── Gardener
   │                           │
   │                           ▼
   │                     Dev (implements)
   │                           │
   │                           ▼
   │                     Review (approves/rejects)
   │                           │
   │                           ▼
   ▼                        Merged
Predictor ──challenges──▶ Planner (triages predictions)
Supervisor ──monitors──▶ All agents (health, escalation)
Vault ──gates──▶ Action, Dev (dangerous operations)
Exec ──delegates──▶ Issues (never writes code directly)

Issue lifecycle

backlogin-progress → PR → CI → review → merge → closed.

Key labels: backlog, priority, in-progress, blocked, underspecified,

tech-debt, vision, action, prediction/unreviewed.

Issues declare dependencies in a ## Dependencies section listing #N

references. Dev-poll only picks issues whose dependencies are all closed.

Available scripts

  • scripts/factory-status.sh — Show agent status, open issues, and CI

pipeline state. Pass --agents, --issues, or --ci for specific sections.

  • scripts/file-issue.sh — Create an issue on the forge with proper labels

and formatting. Pass --title, --body, and optionally --labels.

  • scripts/read-journal.sh — Read agent journal entries. Pass agent name

(planner, supervisor, exec) and optional --date YYYY-MM-DD.

Common workflows

1. Check factory health

bash scripts/factory-status.sh

This shows: which agents are active, recent open issues, and CI pipeline

status. Use --agents for just the agent status section.

2. Read what the planner decided today

bash scripts/read-journal.sh planner

Returns today's planner journal: predictions triaged, prerequisite tree

updates, top constraints, issues created, and observations.

3. File a new issue

bash scripts/file-issue.sh --title "fix: broken auth flow" \
  --body "$(cat scripts/../templates/issue-template.md)" \
  --labels backlog

Or generate the body inline — the template shows the expected format with

acceptance criteria and affected files sections.

4. Check the dependency graph

python3 "${PROJECT_REPO_ROOT}/lib/build-graph.py" \
  --project-root "${PROJECT_REPO_ROOT}" \
  --output /tmp/graph-report.json
cat /tmp/graph-report.json | jq '.analyses'

The graph builder parses VISION.md, the prerequisite tree, formulas, and open

issues. It detects: orphan issues (not referenced), dependency cycles,

disconnected clusters, bottleneck nodes, and thin objectives.

5. Query a specific CI pipeline

bash scripts/factory-status.sh --ci

Or query Woodpecker directly:

curl -s -H "Authorization: Bearer ${WOODPECKER_TOKEN}" \
  "${WOODPECKER_SERVER}/api/repos/${WOODPECKER_REPO_ID}/pipelines?per_page=5" \
  | jq '.[] | {number, status, commit: .commit[:8], branch}'

6. Read and interpret VISION.md progress

Read VISION.md at the repo root for the full vision. Then cross-reference

with the prerequisite tree:

cat "${PROJECT_REPO_ROOT}/planner/prerequisite-tree.md"

The prerequisite tree maps vision objectives to concrete issues. Items marked

[x] are complete; items marked [ ] show what blocks progress. The planner

updates this daily.

Gotchas

  • Single-threaded pipeline: only one issue is in-progress per project at a

time. Don't file issues expecting parallel work.

  • Secrets via env vars only: never embed secrets in issue bodies, PR

descriptions, or comments. Use $VAR_NAME references.

  • Formulas are not skills: formulas in formulas/ are TOML issue templates

for multi-step agent tasks. Skills teach assistants; formulas drive agents.

  • Predictor journals: the predictor does not write journal files. Its memory

lives in prediction/unreviewed and prediction/actioned issues.

  • State files: agent activity is tracked via state/.{agent}-active files.

These are presence files, not logs.

  • ShellCheck required: all .sh files must pass ShellCheck. CI enforces this.

版本历史

共 1 个版本

  • v0.1.1 当前
    2026-05-07 07:54 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

dev-programming

Disinto Factory

johba37
设置和运营disinto自主代码工厂。用于引导新工厂实例、检查代理和CI、管理积压工作或故障排除。
★ 0 📥 405
ai-agent

Agent Browser

rez0
用于 AI 代理的浏览器自动化 CLI。当用户需要与网站交互(包括浏览页面、填写表单、点击按钮、截图等)时使用。
★ 852 📥 334,269
ai-agent

self-improving agent

pskoett
记录自身发现以实现自我改进的技能
★ 4,136 📥 910,804