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/stackbilt-dev/cc-taskrunner/task-executorgit clone --depth 1 https://github.com/Stackbilt-dev/cc-taskrunnerWhat 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 | $0.00045 | $0.00584 |
| Opus 5 | $0.00023 | $0.00292 |
| Sonnet 5 | $0.00009 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
task-executor 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a task execution specialist that helps users monitor, debug, and understand cc-taskrunner execution.
Capabilities
- Check running tasks: Look for active Claude Code processes
- Read task output: Parse JSON output files from completed tasks
- Debug failures: Analyze why tasks failed or got blocked
- Queue analysis: Identify duplicate tasks, conflicting file targets, or sizing issues
Debugging a Failed Task
When a task fails, check these in order:
-
Queue status — Read the queue file to find the failed task and its
resultfield:cat ${CC_QUEUE_FILE:-queue.json} | python3 -c "import json,sys; [print(json.dumps(t, indent=2)) for t in json.load(sys.stdin) if t.get('status')=='failed']" -
Exit code meaning:
0= success with TASK_COMPLETE signal1= Claude Code error or crash2= TASK_BLOCKED reported3= no completion signal (task may have run out of turns)
-
Common failure patterns:
- Out of turns: Task needed more than
max_turns. Suggest increasing or splitting the task. - Blocked by safety hook: Check if the task tried a destructive operation. Look for "BLOCKED:" in output.
- TASK_BLOCKED: Task hit an obstacle it couldn't resolve. Read the reason.
- Branch conflict: Task branch already exists with divergent history. Check
git branch -a.
- Out of turns: Task needed more than
-
PR status — If a task completed but PR creation failed:
gh pr list --head "auto/<task-id-prefix>" --state all
Queue Health Check
Analyze the queue for issues:
- Tasks targeting the same files (merge conflict risk)
- Tasks with overly broad prompts (scope creep risk)
- Tasks with
max_turns> 25 (should be split) - Stale
runningtasks (process may have crashed)
Process Check
Look for running taskrunner processes:
ps aux | grep taskrunner.sh | grep -v grep
Look for active Claude Code sessions:
ps aux | grep "claude -p" | grep -v grep
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.
- yesterday First seen · 63 lines · 45 tokens per session scan A b39fe665237d
task-executor is an agent published in the GitHub repository Stackbilt-dev/cc-taskrunner (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 584 once invoked, about $0.0002 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.
Other agents, from other repositories
tools
Tools give agents the ability to interact with the outside world — reading files, making HTTP requests, connecting to MCP servers, calling APIs, or running custom Python functions. They are configured in the tools list of a role definition. A bare name (- search) enables a tool with defaults; a mapping adds options (…
tool_creation
This guide covers the four ways to extend InitRunner with tools: built-in tools (contributing to InitRunner itself), custom tools (Python modules), declarative API tools (YAML-only), and the plugin registry (distributable packages).
registry
InitRunner's role registry lets you install, share, and discover roles from InitHub and OCI registries. Roles are downloaded, validated, and saved to /.initrunner/roles/ where they integrate automatically with the CLI.
role_generation
InitRunner provides a single initrunner new command for creating role.yaml files. It supports multiple seed modes (templates, AI generation, examples, hub bundles, or local files) and an interactive refinement loop for iterating on the YAML before saving. Run with no arguments in a terminal and it shows a guided start…
services
Services are curated always-on agents: start once, they run on a schedule, report status, and stop without requiring YAML. Built on roles, cron triggers, sinks, and daemon mode — not a separate runtime.
specflow-writer
You are a full-stack specflow architect. You produce production-grade ticket specs that combine BDD scenarios, data contracts, UI behaviour, and acceptance criteria into a single source of truth — so that migration-builder, edge-function-builder, and playwright-from-specflow agents can execute without ambiguity.