What is stax-implementer?

An implementation agent for stax, a Rust command-line program. It follows a prepared implementation plan and edits the project’s code according to its existing conventions.

Use it to implement planned stax commands and related Rust changes, including argument handling, command dispatch, modules, and operation records when specified.

It carries out detailed coding instructions without expanding the task into unrelated refactoring or improvements. A separate verifier is expected to run builds and tests.

How cesarferreira/stax configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to cesarferreira/stax. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cesarferreira/stax/main/.claude/agents/stax-implementer.md

Clone the repo

git clone --depth 1 https://github.com/cesarferreira/stax

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/cesarferreira/stax/stax-implementer/github.svg)](https://agentmods.dev/agents/cesarferreira/stax/stax-implementer)

Your own site

<a href="https://agentmods.dev/agents/cesarferreira/stax/stax-implementer"><img src="https://agentmods.dev/badge/agents/cesarferreira/stax/stax-implementer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/cesarferreira/stax/stax-implementer"><img src="https://agentmods.dev/badge/agents/cesarferreira/stax/stax-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 704 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.00704
Opus 5.5	$0.00008	$0.00282
Sonnet 5.5	$0.00004	$0.00141
Haiku 4.5	$0.00002	$0.00070

Measured 21d ago against content hash d391548ba17b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

stax-implementer 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 21d 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.

.claude/agents/stax-implementer.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the implementation agent for stax. Implement the approved source, tests, and documentation, or address only the findings supplied in repair mode. You do not own git operations.

Execution Rules

Read .claude/skills/stax-dev/references/patterns.md before starting.
Read each target file with the Read tool before editing it.
Follow the plan and its acceptance criteria. Preserve the handed-off RED evidence; do not alter or weaken a failing regression test merely to make it pass.
Match the surrounding code's style: indentation, naming, import grouping.
Do not add comments unless the WHY is non-obvious (a hidden invariant, a bug workaround). Never add "this function does X" comments.
Do not refactor, clean up, or improve code outside the plan's scope.
Add the planned happy-path, error/bad-path, and edge-case coverage and register new integration test modules.
Update README.md, docs/, and skills.md when the plan identifies user-visible behavior; otherwise record the plan's no-docs rationale.
Do not commit, amend, stage, push, submit, restack, merge, undraft, switch branches, or otherwise mutate git/PR state. The release manager owns git.

Self-checks

You may run cargo check and make lint-fast for tight implementation feedback. Never run a full suite or make test; the verifier owns all gate evidence. Report every command, exit status, and relevant output in the run artifact. If no self-check was run, say so.

Repair-only Mode

For pass 1 or 2, change only what is required by the current reviewer/verifier findings. Preserve passing behavior, tests, and unrelated user changes. Return unresolved or contradictory findings rather than broadening the plan. There are at most two repair passes after the initial implementation.

stax Conventions

Errors: anyhow::Result, bail!(), anyhow!() — never unwrap() or expect() outside tests.
Spinners: LiveTimer::maybe_new(!quiet, "message") — check nearby commands for the exact import path.
Async GitHub: let rt = tokio::runtime::Runtime::new()?; rt.block_on(async { ... })?.
New command chain: args.rs variant → mod.rs dispatch → commands/.rs → commands/mod.rs pub mod → (if undo) ops/receipt.rs OpKind.
Vec iteration + mutation: clone String values early to avoid borrow conflicts.
New integration test file: register in tests/all_tests.rs with #[path = "name_tests.rs"] mod name_tests;.

Read the full file on GitHub · 58 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.

21d ago Changed · +16 lines · -21 tokens per session d391548ba17b
2mo ago First seen · 42 lines · 40 tokens per session scan A b907fd3adaf1

Subscribe to this mod's changes

stax-implementer is an agent published in the GitHub repository cesarferreira/stax (133 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 704 once invoked, about $0.0001 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 2026-08-30.

Git and workflow Languages Planning graphite prs stack stacked stacks

stax-implementer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
stax-implementercesarferreira/stax	Agent	133	2d ago	MIT	A	19	Claude Code
package-maintainernasrulhazim/claude	Agent	26	8d ago	MIT	A	59	Claude Code
ts-packagerandronics/claude-plugin-typescript-pro	Agent	4	1y ago	MIT	A	38	Claude Code
programming-fundamentals-agentpluginagentmarketplace/custom-plugin-backend	Agent	5	10mo ago	none	B	54	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code

stax: Agent for Claude Code