Task Execution

A prompt for carrying out one assigned task from a collaborative plan across multiple agents or people. It sets the repository, task scope, branch rules, commit format, and testing expectations.

In plain words
What is it for?
Use it when implementing one numbered repository task, documenting blockers, running available tests, and committing the completed changes on the current feature branch.
Why use it?
It keeps work separated so an agent does not take on other tasks or accidentally combine changes from different branches.

Skill for Claude CodeCodex

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 skills/internet-development/ts-general-agent/task-execution
Any agent
npx skills add internet-development/ts-general-agent --skill task-execution
Clone the repo
git clone --depth 1 https://github.com/internet-development/ts-general-agent

Made for: Claude Code, Codex.

Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 491 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 $0.00016 $0.00491
Opus 5 $0.00008 $0.00246
Sonnet 5 $0.00003 $0.00098
Haiku 4.5 $0.00002 $0.00049

Measured 2d ago against content hash 520c74d3c8e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Task Execution 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.

skills/task-execution/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Prompt

You are executing a task from a collaborative multi-SOUL plan.

Repository: {{repoFullName}} Plan: {{planTitle}} Goal: {{planGoal}}


Your Task: Task {{taskNumber}} - {{taskTitle}}

{{filesSection}}

{{dependenciesSection}}

Description: {{taskDescription}}


Constraints

  1. Stay focused on THIS task only - Do not work on other tasks
  2. Never commit directly to main - You are on a feature branch, commit there
  3. NEVER run git merge, git rebase, git pull, or git fetch — your feature branch must contain ONLY your task's commits, nothing else. Merging other branches contaminates the PR with unrelated commits.
  4. NEVER switch branches — stay on the current feature branch for the entire task. Do not git checkout main or any other branch.
  5. Commit your changes with message: task({{taskNumber}}): {{taskTitle}}
  6. Commit with descriptive messages referencing the task number in each commit
  7. If blocked, explain clearly what's preventing completion
  8. Test your changes if tests exist — but if the test runner is not installed (e.g. vitest: command not found, jest: not found), that is NOT a task failure. Skip tests and continue. The verification system handles this separately.
  9. Keep changes minimal - only what's needed for this task
  10. You MUST produce at least one git commit with file changes. The verification system requires git changes on the feature branch. If the task description seems to require only non-code actions (posting comments, updating issues), translate it into a file change — update documentation, a tracking file, or a relevant config. A task with zero git changes will fail.

Process

  1. Read and understand the task description
  2. Explore the codebase to understand context
  3. Verify you are on the correct feature branch (run git branch to confirm — NOT main)
  4. Make the necessary changes
  5. Test if possible
  6. Commit with the specified message format
  7. Report what was done

Read the full file on GitHub · 51 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. 2d ago First seen · 51 lines · 16 tokens per session scan A 520c74d3c8e9

Subscribe to this mod's changes

Task Execution is a skill published in the GitHub repository internet-development/ts-general-agent (11 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 491 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories