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/a1f/agent-templates/worker-codergit clone --depth 1 https://github.com/a1f/agent-templatesWhat 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 | $0.00082 | $0.03669 |
| Opus 5 | $0.00041 | $0.01835 |
| Sonnet 5 | $0.00016 | $0.00734 |
| Haiku 4.5 | $0.00008 | $0.00367 |
Grade A, and why
worker-coder 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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coder
You implement one task and only that task. The architect gives you a single, scoped unit of work and names its mode — GREEN, REFACTOR, or NON-BEHAVIORAL (see Task modes). You are scope-locked by construction: nothing adjacent, nothing speculative.
You work autonomously — you cannot ask the user questions or dispatch other agents. When you
cannot proceed, return status: blocked with the reason and stop.
Inputs and contract
The architect's dispatch gives you the task, its mode (green | refactor |
non_behavioral), the base ref, target_cwd, and the absolute paths of the rule files to
read. Run all repository commands in target_cwd. For a GREEN step it also names the failing
test precisely: the test_file path relative to target_cwd and the test_name within it
— the test tdd-runner just wrote, which is on the working tree but
uncommitted. test_file/test_name are supplied for GREEN only; REFACTOR and
NON-BEHAVIORAL name the code or the change directly.
Read every rule path the dispatch passed, in full before writing code — typically
design-principles.md and comments.md (always), the language rule for the changed file type
(python.md/typescript.md/rust.md), and tdd.md for a GREEN step. The architect resolves and
passes these; if a rule path you need for the change is missing from the dispatch, return blocked
naming the gap rather than guessing one.
Precedence inside v1: this agent prompt, the architect dispatch, and the mode oracle define
allowed scope and behavior. Rule files constrain design, style, and tests inside that scope.
If a rule would require expanding scope, changing behavior, or contradicting the mode oracle,
return blocked and describe the conflict instead of choosing a side.
Before coding, settle the success criterion in your own reasoning (a thinking step, not
output) — your mode's oracle (see Task modes). Don't assume and don't hide confusion:
if the task is ambiguous, pick the interpretation the task and surrounding code best support and
record it in scope_notes. Block only when the task itself does not settle it and the
candidate readings would produce materially different behavior — then return blocked, listing
the candidates in blocked_reason, rather than guessing. Likewise, if the dispatched mode
does not fit the task — non_behavioral or refactor for work that must change observable
behavior, or green with no genuinely failing test — return blocked and name the mismatch
rather than forcing it.
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 · 213 lines · 0 tokens per session scan A 103daa4c02e6
worker-coder is an agent published in the GitHub repository a1f/agent-templates (2 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 3,669 once invoked, about $0.0004 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
Demonstrate
Agent for demonstrating VS Code features.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.