A software inspection skill that checks an implementation against design documents such as API specifications, quality-assurance scenarios, flow diagrams, and other project specifications.

Use it with /argos for final acceptance reviews of software against its design and test materials.

It helps find differences between what was designed and what was built across runtime behavior, APIs, testing, diagrams, and security.

argos — Skill for Claude Code and Codex by Dannykkh/skill-olympus

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.

Any agent

npx skills add Dannykkh/skill-olympus --skill argos

Clone the repo

git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Made for: Claude Code, Codex.

Or install skill-olympus, the plugin that ships this one along with the rest of its 101 skills, 7 commands, 5 MCP servers.

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/skills/dannykkh/skill-olympus/argos/github.svg)](https://agentmods.dev/skills/dannykkh/skill-olympus/argos)

Your own site

<a href="https://agentmods.dev/skills/dannykkh/skill-olympus/argos"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/argos/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/skills/dannykkh/skill-olympus/argos"><img src="https://agentmods.dev/badge/skills/dannykkh/skill-olympus/argos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,207 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 292
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.

How audits are shown

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	$0.00089	$0.08207
Opus 5.5	$0.00036	$0.03283
Sonnet 5.5	$0.00018	$0.01641
Haiku 4.5	$0.00009	$0.00821

Measured 3d ago against content hash 02162852a741, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

argos 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 3d 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.

skills/argos/SKILL.md · 544 lines

How it starts

The opening of the file, as written. The whole thing — 544 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Argos (아르고스) — 100개의 눈으로 검증하는 감리

아르고스 판옵테스(Argus Panoptes): 100개의 눈을 가진 그리스 신화의 감시자. 설계 도면과 스펙 대비 구현 상태를 빠짐없이 검증합니다.

GS 작업을 전달받은 경우에만

GS 인증 사전점검에서 등급·기관 기준·run_dir을 전달받으면 gs-certification 모듈을 프로젝트 실제 경로 → 현재 CLI 활성 루트 → SKILLS-CATALOG.md의 정확한 source-only 경로로 해석한다. 그 SKILL.md를 읽고 부모 디렉터리의 references/argos-gs-audit.md를 적용한다. GS 입력이 없는 일반 실행은 기존 절차를 따른다. 필수 참조 누락은 NOT RUN으로 반환한다. 사용자의 점검/수정 권한과 GS 출력 경로를 우선하고 기존 latest 보고서를 덮어쓰지 않는다.

Quick Start

/argos                              # planning_dir 자동 탐색
/argos docs/plan/my-feature         # 특정 계획 디렉토리 지정
/argos --phase 5                    # 특정 Phase만 실행

공식 호출명: /argos (별칭: 아르고스, 감리)

내부 소스 모듈 해석 계약 (필수)

code-reviewer, flow-verifier, frontend-design, ui-ux-auditor는 Argos 안에서 호출하는 등록 스킬이 아니라, 절차와 기준을 직접 읽는 source-only 내부 모듈입니다. 각 이름에 대해 해석된 SKILL.md 절대경로를 MODULE_SKILL[name], 그 부모 디렉터리를 MODULE_ROOT[name]으로 기록합니다.

각 모듈을 처음 쓰기 전에 다음 순서로 해석합니다.

프로젝트 루트의 skills/<name>/SKILL.md가 실제 파일로 존재하고 frontmatter의 name이 정확히 <name>일 때만 그 절대경로를 사용합니다. 없거나 이름이 다르면 프로젝트의 다른 경로를 추측하지 않고 2번으로 갑니다.
없으면 현재 런타임의 활성 루트에서 정확한 skills/<name>/SKILL.md를 확인합니다. Codex는 $CODEX_HOME/skills(미설정이면 ~/.codex/skills), Claude와 Grok 호환 표면은 ~/.claude/skills, Antigravity는 ~/.gemini/antigravity-cli/skills입니다. 파일 존재와 frontmatter 이름이 모두 일치할 때만 사용하고, 아니면 3번으로 갑니다.
없으면 현재 런타임의 전역 SKILLS-CATALOG.md를 읽습니다. Codex는 $CODEX_HOME/SKILLS-CATALOG.md(미설정이면 ~/.codex/SKILLS-CATALOG.md), Claude와 Grok 호환 표면은 ~/.claude/SKILLS-CATALOG.md, Antigravity는 ~/.gemini/antigravity-cli/SKILLS-CATALOG.md입니다. 첫 번째 셀이 정확히 <name>인 행 (| <name> | ... | ... | <읽을 경로> |) 하나를 찾아 읽을 경로의 절대 SKILL.md를 그대로 사용합니다. 정확한 이름의 행이 0개이거나 2개 이상이면 해석 실패이며 다른 행이나 레지스트리 경로를 추측하지 않습니다.
해석한 파일의 존재를 확인하고 SKILL.md 전체를 읽은 뒤에만 그 모듈의 기준을 적용합니다. 참조 파일은 MODULE_ROOT[name]/references/..., 스크립트는 MODULE_ROOT[name]/scripts/...로부터 절대경로를 만듭니다.

이 과정은 모듈 읽기이지 스킬 호출이 아닙니다. /code-reviewer, /flow-verifier, /frontend-design, /ui-ux-auditor를 호출하거나 스킬 레지스트리에 등록됐다고 가정하지 않습니다. 프로젝트·활성 루트 파일도 없고 카탈로그의 정확한 행·읽을 경로·필수 참조 중 하나라도 없으면 보고서의 Module Coverage에 경로와 이유를 기록하고 아래의 한정된 native fallback을 사용합니다. fallback도 실행할 수 없는 검사는 NOT RUN 또는 UNVERIFIED로 남기며 PASS로 바꾸지 않습니다.

Read the full file on GitHub · 544 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

3d ago Changed · +1 lines 02162852a741
19d ago Changed · +21 lines 4411952a9f7b
22d ago Changed · +20 lines caf30dd5c754
1mo ago Changed · +19 lines c7c2bd12740f
1mo ago Changed aa9a0bde0132
1mo ago First seen · 483 lines · 89 tokens per session scan A 5db93eb4dd85

Subscribe to this mod's changes

argos is a skill published in the GitHub repository Dannykkh/skill-olympus (7 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 8,207 once invoked, about $0.0004 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 2026-08-31.

Claude Code Code review ai-agent ai-automation ai-coding claude-code-agents claude-code-hooks

audit-project

Audits the Claude Code configuration of a project against the dotforge template. Generates a report with score and gaps.

luiseiman/dotforge · 26 tokens

project-audit

Repository audit for non-website projects (CLI, libs, backend, monorepo). Use when: "project-audit", "project audit", "repo audit", "code audit".

claude-hangar/claude-hangar · 42 tokens

adversarial-review

Critical review (min. 5 findings). Modes: code, audit, plan. Use when: "review", "critical review", "code review", "plan review", "audit review".

claude-hangar/claude-hangar · 44 tokens

inline-review

Quick self-review checklist after code changes. Lightweight alternative to adversarial-review. Use when: "review my changes", "self-review", "quick review", "check my work", or automatically after significant edits.

claude-hangar/claude-hangar · 45 tokens

review-team

Launch parallel code review agents for comprehensive multi-perspective review. Use when: "review team", "full review", "multi-review", "review-team".

claude-hangar/claude-hangar · 34 tokens

factory-ci

CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…

nonlinear-xyz/factory-kit · 110 tokens