A small coding task that turns a retry pseudocode example into an executable Python safety mechanism with dummy components.

Use it to run success and failure demonstrations from the command line without external packages, network access, or file-system calls.

It makes the example runnable while preserving its three-attempt limit and its manual-escalation outcome after repeated failures.

code-author — Agent for Claude Code by revfactory

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.

Clone the repo

git clone --depth 1 https://github.com/revfactory/harness-engineering-with-cc

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/revfactory/harness-engineering-with-cc/code-author/github.svg)](https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/code-author)

Your own site

<a href="https://agentmods.dev/agents/revfactory/harness-engineering-with-cc/code-author"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/code-author/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/revfactory/harness-engineering-with-cc/code-author"><img src="https://agentmods.dev/badge/agents/revfactory/harness-engineering-with-cc/code-author.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 387 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	$0.00040	$0.00387
Opus 5.5	$0.00016	$0.00155
Sonnet 5.5	$0.00008	$0.00077
Haiku 4.5	$0.00004	$0.00039

Measured 2mo ago against content hash e0161b2f10c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

code-author 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.

ex-08-15-max-retries-code/.claude/agents/code-author.md · 42 lines

What it actually says

역할

책 p140의 MAX_RETRIES = 3 안전장치 의사코드를 시그니처 그대로 보존하면서, 표준 라이브러리만으로 실행 가능하도록 더미 generator/verifier 스텁을 채워 넣는다.

보존해야 할 책 시그니처

MAX_RETRIES = 3

for attempt in range(MAX_RETRIES):
    artifact = generator.run(spec)
    result = verifier.run(artifact)
    if result.passed:
        return artifact

return f"escalated: {MAX_RETRIES}회 실패, 수동 개입 필요"

작업 단계

책 의사코드를 run/max_retries.py에 그대로 옮긴다 (변수명·문구·return 형식 유지).
더미 CodeGenerator·TestRunner 클래스 추가 — 표준 라이브러리만 사용.
CLI 인자(success/fail)로 두 시나리오 분기.
if __name__ == "__main__": 진입점에서 두 시나리오 실행 가능하게 한다.

금지 사항

외부 패키지 import 금지 (표준 라이브러리만).
책 문구 "escalated: 3회 실패, 수동 개입 필요" 변경 금지.
네트워크/파일 외부 호출 금지.

출력

run/max_retries.py만 작성한다. 실행은 runner 에이전트가 담당.

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.

2mo ago First seen · 42 lines · 40 tokens per session scan A e0161b2f10c9

Subscribe to this mod's changes

code-author is an agent published in the GitHub repository revfactory/harness-engineering-with-cc (123 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 387 once invoked, about $0.0002 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.

Languages Python Testing

code-author next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
code-authorrevfactory/harness-engineering-with-cc	Agent	123	5mo ago	Apache-2.0	A	40	Claude Code
Geoprocessing SpecialistSHAdd0WTAka/Zen-Ai-Pentest	Agent	504	4d ago	MIT	A	45	Claude Code, OpenCode
python-proechoVic/blade-code	Agent	181	25d ago	MIT	A	51	Claude Code
temporal-test-buildercanonical/copilot-collections	Agent	32	today	Apache-2.0	A	56	Claude Code
package-revieweroborchers/fractional-cto	Agent	36	13d ago	MIT	A	287	Claude Code
script-operatorMadGraphTeam/MadAgents	Agent	15	3mo ago	MIT	A	24	Claude Code
python-reviewerFmarzochi/EGC	Agent	68	today	Apache-2.0	A	43	Claude Code, Kiro