cc-taskrunner CLAUDE.md

A task queue and runner for Claude Code, with safety checks, separate branches, and pull-request creation. A task queue is a list of jobs that can be processed one after another.

In plain words
What is it for?
Adding and processing queued tasks, limiting or continuously running the queue, previewing changes, and pulling fixes from a Cloudflare D1 database.
Why use it?
It removes repeated manual work when running many coding tasks and provides dry-run and timeout options for safer control.

Instructions file

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/stackbilt-dev/cc-taskrunner/claude-md
Clone the repo
git clone --depth 1 https://github.com/Stackbilt-dev/cc-taskrunner
Per session 545 This file is loaded in full into every session.
When invoked 545 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 $0.00545 $0.00545
Opus 5 $0.00272 $0.00272
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00055 $0.00055

Measured yesterday against content hash da8dd971845d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-taskrunner CLAUDE.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 yesterday.

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.

CLAUDE.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cc-taskrunner

Autonomous task queue for Claude Code with safety hooks, branch isolation, and PR creation.

Commands

  • ./taskrunner.sh — Run until queue empty
  • ./taskrunner.sh --max N — Run at most N tasks
  • ./taskrunner.sh --loop — Loop forever (poll every 60s)
  • ./taskrunner.sh --dry-run — Preview without executing
  • ./taskrunner.sh add "title" — Add a task to the queue
  • ./taskrunner.sh pull --fix-id <uuid> — Pull a QUEUED fix from CodeBeast D1 into queue.json
  • ./taskrunner.sh pull --fix-id <uuid> --dry-run — Preview D1 row without writing anything

Key env vars

  • CC_TASK_TIMEOUT — Watchdog timeout in seconds (default 1500 / 25 min); tasks exceeding this are marked TASK_BLOCKED
  • CLOUDFLARE_API_TOKEN / CF_ACCOUNT_ID / D1_FIX_QUEUE_DB_ID — Required for pull subcommand

Structure

  • taskrunner.sh — Main script (~1150 lines bash + embedded python)
  • hooks/ — Safety hook scripts (block-interactive, safety-gate, syntax-check)
  • queue.json — Task queue file (JSON array, gitignored; see queue.example.json)
  • repo-aliases.conf — Repo alias mappings (gitignored; see repo-aliases.example.conf)
  • scripts/ — Helper scripts (deploy, pull-fix.sh, cleanup-branches.sh)
  • plugin/ — Plugin system (agents, commands, safety)

Conventions

  • Bash 4+, Python 3 for JSON manipulation
  • All paths relative to script directory
  • Tasks use JSON format with id, title, repo, prompt, status fields
  • Completion signal: TASK_COMPLETE or TASK_BLOCKED

OSS Policy

This is a public infrastructure package governed by the Stackbilt OSS Infrastructure Package Update Policy.

Rules:

  1. Additive only — never remove or rename public API without a major version bump
  2. No product logic — framework patterns and generic utilities only. If a competitor could reconstruct Stackbilt product architecture from this code, it doesn't belong here.
  3. Strict semver — patch for fixes, minor for new features, major for breaking changes
  4. Tests travel with code — every public export must have test coverage
  5. Validate at boundaries — all external API responses validated before returning to consumers

Read the full file on GitHub · 42 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. yesterday First seen · 42 lines · 545 tokens per session scan A da8dd971845d

Subscribe to this mod's changes

cc-taskrunner CLAUDE.md is an instructions file published in the GitHub repository Stackbilt-dev/cc-taskrunner (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 545 tokens to every session, about $0.0027 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 2026-08-31.