Home / Skills / old-coder

old-coder

Evidence-first development — surround the implementation with an executable spec and a gauntlet of constraints (tests, types, coverage, mutation) so line-by-line review becomes optional. Use when the user explicitly asks for high-assurance or evidence-first work ("reliable", "TDD", "prove it works", "I won't read the code"), or when the change touches high-stakes domains (money, auth, data loss, concurrency, public API). For routine changes where the user just wants normal tests, write good tests directly instead of invoking this loop.

ScannedSkillSource: GitHub

753 stars +5 this week Updated 3mo ago License MIT Context ≈138 tokens always loaded

69popular

Why this score

Stars

18/35

Usage (forks)

6/15

Upkeep

20/25

License

15/15

Owner history

10/10

This repo hosts 2 skills, so its 753 stars are split between them (about 377 each) for scoring.

Popularity score: 69/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Oct 20, 2026 at commit a0eb529d393a, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

Name	Score	Stars	Context	Updated
This oneold-coder AmazingAng/old-coder · Skill	69	★ 753	≈138 always	3mo ago
coder mverab/eGEOagents · Subagent Both about coder	66	★ 204	≈23 in chat	16d ago
html-coder TokenRhythm/opensquilla · Skill Both about coder and development	74	★ 7.1k	≈92 always	16d ago
experiment-coder AutoResearch-Factory/Agon · Subagent Both about coder	52	★ 54	≈26 in chat	29d ago
rust-coder onsails/skills · Subagent Both about coder and implementation	51	★ 44	≈59 in chat	2mo ago
experiment-iterative-coder EvoScientist/EvoSkills · Skill Both about coder and explicitly	56	★ 481	≈157 always	1mo ago

Install

mkdir -p .claude/skills/old-coder

curl -sL https://codeload.github.com/AmazingAng/old-coder/tar.gz/a0eb529d393a1cb3ccc564e32b2104e7e75c7a29 | tar -xz -C .claude/skills/old-coder --strip-components=3 "old-coder-a0eb529d393a1cb3ccc564e32b2104e7e75c7a29/skills/old-coder"

To remove it later:

rm -rf .claude/skills/old-coder

npx skills add AmazingAng/old-coder --skill old-coder

Pinned to commit a0eb529d393a as listed by GitHub.

Context cost: ≈138 tokens loaded every session (name and description), plus ≈5.4k tokens when the skill is used.

The Claude Code command downloads this skill folder at the pinned commit into .claude/skills/. The Skills CLI (npx skills) works with many agents but can't pin a version, so it installs whatever is current.

Used for

Engineering › Testing & QA

Facts

Repo: AmazingAng/old-coder
Stars: 753
Forks: 63
Last push: 2026-08-18 (3mo ago)
License: MIT
Owner: AmazingAng · since 2015
Language: Python
Works with: Claude Code, Skills CLI