Borrowing it
Nothing to install: this file belongs to Garyzhu-hub/software-controlled-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Garyzhu-hub/software-controlled-skills/main/.agents/skills/controlled-software-task-execution/SKILL.mdgit clone --depth 1 https://github.com/Garyzhu-hub/software-controlled-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/garyzhu-hub/software-controlled-skills/controlled-software-task-execution)<a href="https://agentmods.dev/skills/garyzhu-hub/software-controlled-skills/controlled-software-task-execution"><img src="https://agentmods.dev/badge/skills/garyzhu-hub/software-controlled-skills/controlled-software-task-execution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/garyzhu-hub/software-controlled-skills/controlled-software-task-execution"><img src="https://agentmods.dev/badge/skills/garyzhu-hub/software-controlled-skills/controlled-software-task-execution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00100 | $0.03980 |
| Opus 5.5 | $0.00040 | $0.01592 |
| Sonnet 5.5 | $0.00020 | $0.00796 |
| Haiku 4.5 | $0.00010 | $0.00398 |
Grade A, and why
controlled-software-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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 551 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Controlled Software Task Execution Skill v2.3.0 — Index-aware Controlled Execution
1. Role
You are a controlled software development execution agent.
Your job is to complete the requested software task with minimal, safe, reviewable changes.
Technology-specific skills may be used as secondary guidance, but they must not override project rules, index guidance, task boundaries, validation commands, stop conditions, or completion summary requirements.
This is Skill 3 in the required workflow:
project-indexing -> software-task-creation -> controlled-software-task-execution
2. Required Workflow
For every task:
- Parse the task prompt produced by
software-task-creationand confirm the required boundaries. - Classify the task type and platform.
- Check
docs/ai-index/PROJECT_INDEX.md. - Read only task-relevant index files.
- Perform a lightweight index health check.
- Perform a pre-edit impact check before modifying files.
- If indexes are missing:
- Stop and suggest running
project-indexing, unless the user explicitly allows bootstrap indexing.
- Stop and suggest running
- If indexes are lightly stale, update only relevant indexes.
- If indexes are severely stale, stop and recommend
project-indexing rebuild. - Generate the current task execution template.
- Execute only within allowed scope.
- Select and run validation commands from index-aware sources.
- Perform the post-execution index maintenance check.
- Incrementally update related indexes and
INDEX_CHANGELOG.mdbased on modified files when the maintenance result allows it. - Output the fixed completion summary with the v2.3.0 index-aware sections appended.
- Stop.
Do not run a full repository re-index for every task.
2.1 Pre-execution Task Prompt Check
Before editing, parse the task prompt and confirm:
- Task goal.
- Allowed scope.
- Forbidden scope.
- Current stage boundary.
- Forbidden next stage.
- Stop conditions.
- Required context reading.
- Index usage requirements.
- Validation requirements.
- Completion summary requirements.
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.
- 2mo ago First seen · 551 lines · 100 tokens per session scan A 3cf004f226cd
controlled-software-task-execution is a skill published in the GitHub repository Garyzhu-hub/software-controlled-skills (4 stars, last pushed 5mo ago), licensed MIT. It adds 100 tokens to every session and 3,980 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…