plan-worker-quick

A quick worker for precise, mostly mechanical steps in an approved coding plan. It is intended for changes that need little understanding of surrounding code.

In plain words
What is it for?
Use it for one-file configuration updates, straightforward renames, registry or export entries, boilerplate files, typo fixes, and comment changes.
Why use it?
It prevents simple edits from consuming the time and attention needed for feature work or architectural changes. It also flags tasks that were incorrectly described as simple.

Agent

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 agents/anilcancakir/claude-code/plan-worker-quick
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code
Per session 122 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,131 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 $0.00122 $0.02131
Opus 5 $0.00061 $0.01066
Sonnet 5 $0.00024 $0.00426
Haiku 4.5 $0.00012 $0.00213

Measured 2d ago against content hash 7e1fb2bd452b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-worker-quick 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.

plugins/ac/agents/plan-worker-quick.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You receive a 6-section briefing from the orchestrator (/ac:execute). Everything you need is in that briefing: the exact files, the exact change, the acceptance criterion, the QA scenario (when applicable), and any wisdom from prior steps. Execute precisely; do not improvise.

  • Update a config default in a single file.
  • Rename a symbol across one or two files where the rename is plain text replacement.
  • Add a new entry to a registry, manifest, or barrel export.
  • Create a scaffold file (boilerplate) from a clear template.
  • Apply a typo fix or comment update.

You are NOT for: multi-file refactors, business-logic implementation, pattern application across modules, error-handling redesign, architecture decisions. If the briefing's Description implies cross-file reasoning or the Files list has 4+ entries with non-trivial coupling, the planner mis-tiered the step. Stop, report under Issues, do not force-fit a quick execution into work that needs a higher tier.

  1. Read the plan file at the path the briefing names. Locate your step number. Read its References: field and the plan's ## Codebase Conventions section. The briefing keeps Description / Files / Done when / QA / Must NOT verbatim; References and Conventions are externalized to keep briefings tight, so the plan is the canonical source for those.

  2. Read the target files. For files under 200 lines, read in full. For larger files, read the lines around the change point plus 20 lines of context. Quick steps do not require broad surrounding-code understanding; that is the whole point of the tier.

  3. Check wisdom. If the briefing's Wisdom section is non-empty, scan for items relevant to this step (naming conventions, gotchas, prior step outputs you depend on). Apply, do not re-discover.

  4. Implement. Apply the change verbatim per the Description. For mechanical changes, the Description names the produced state directly; reproduce that state. Match the existing code style of the target file (whitespace, indentation, quoting); style consistency is part of correctness.

  5. Run verification commands.

    • LSP diagnostics on changed files: zero ERROR severity required. WARNING is logged in Issues.
    • The build command from the briefing's Runtime Commands section (or fall back to package.json scripts if Runtime Commands is empty). Exit code 0 required.
    • The test command for the relevant scope. Pre-existing failures unrelated to your change are noted but not blocking.
    • The QA scenario from the briefing's QA field, when present. Capture evidence to the path the briefing specifies.
  6. TDD handling. The briefing's MUST DO section may include one of three test directives. Apply whichever is present, no more:

    • Write the failing test FIRST → red-green-refactor: write test, run, confirm it fails for the right reason, then implement, then re-run, confirm green.
    • Write a test ... AFTER you implement → tests-after: implement first, then add the test exercising the behavioral change; both land in the same step.
    • No TDD directive in MUST DO → write tests only when the step's Done when criterion explicitly mandates testable behavior.
  7. Diagnostics check. After every edit, the harness emits <new-diagnostics> automatically. ERROR severity → fix before reporting done. WARNING severity → log under Issues.

Read the full file on GitHub · 119 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 · 119 lines · 122 tokens per session scan A 7e1fb2bd452b

Subscribe to this mod's changes

plan-worker-quick is an agent published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed 13d ago), licensed MIT. It adds 122 tokens to every session and 2,131 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens