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 skills add sramji/awesome-superpowers --skill autonomous-chunk-executiongit clone --depth 1 https://github.com/sramji/awesome-superpowersWrote 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/sramji/awesome-superpowers/autonomous-chunk-execution)<a href="https://agentmods.dev/skills/sramji/awesome-superpowers/autonomous-chunk-execution"><img src="https://agentmods.dev/badge/skills/sramji/awesome-superpowers/autonomous-chunk-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/sramji/awesome-superpowers/autonomous-chunk-execution"><img src="https://agentmods.dev/badge/skills/sramji/awesome-superpowers/autonomous-chunk-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 | $0.00044 | $0.00787 |
| Opus 5 | $0.00022 | $0.00394 |
| Sonnet 5 | $0.00009 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
autonomous-chunk-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 8d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Chunk Execution
Overview
Break large multi-file projects into independently reviewable chunks, each executed as a separate worktree/PR. A YAML tracker on the main branch provides cross-session state; an execution plan in the repo provides detailed per-chunk instructions; a prompt template bootstraps each worker session.
When to Use
- Code review remediation (many fixes across many files)
- Large migrations or refactors that touch 5+ files
- Any project with 5+ independent items that must be done sequentially
- Work that may span multiple sessions or be delegated to worker agents
The Pattern
Three artifacts, all in the repo:
- YAML tracker — per-item and per-chunk status, lives on main
- Execution plan — detailed per-chunk instructions with file paths, verification steps
- Prompt template — paste into each worker session to bootstrap autonomously
Tracker structure
review: <project-name>
started: <date>
chunks:
chunk-name:
branch: <prefix>/chunk-name
status: TODO # TODO | IN_PROGRESS | DONE
pr: null
items: [ITEM1, ITEM2]
items:
ITEM1: {status: TODO, chunk: chunk-name, desc: "what to fix"}
<prefix> = your project's branch-naming convention.
Prompt template
Read <tracker-path> to find the next TODO chunk.
Read <plan-path> for chunk details.
Execute the next TODO chunk:
1. Create an isolated worktree via `superpowers:using-git-worktrees`
2. Work each item, running tests after each fix
3. Finish via `finishing-with-review` (review-gated), then PR/merge per its options
4. Update tracker on main
Chunking Strategy
Order chunks by dependency, not priority:
- Files shared across chunks force sequential execution
- Put highest-risk changes first (fail fast)
- Put the largest refactor last (minimize merge conflicts)
- Group deletions together (low risk, easy to review)
- Each chunk must leave tests passing
Infrastructure Requirements
- Tracker file must be writable on main — ensure your repo's main-branch protection allows direct commits for tracker updates, or use a dedicated state branch
- Plan must be committed to the repo — session-local locations are invisible to other sessions and worker agents
- Each chunk is a separate branch/PR — independently reviewable and revertable
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.
- 8d ago First seen · 91 lines · 44 tokens per session scan A b9faf58df5d3
autonomous-chunk-execution is a skill published in the GitHub repository sramji/awesome-superpowers (3 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 787 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 skills, from other repositories
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.