agentmods.dev

dev-suite: Skill for Claude Code

.gemini/config/skills/engineer/SKILL.md

engineer is a skill for Claude Code, Gemini CLI from kk376/dev-suite. It costs 324 tokens per session (13,262 once invoked), scanned C, original, MIT.

A broad software-engineering skill covering architecture, test-driven development, bug diagnosis, code review, security checks, and interface design.

In plain words
What is it for?
Use it for engineering tasks such as planning features, writing tests, diagnosing bugs, reviewing code, checking defensive security, and designing interfaces.
Why use it?
It provides a structured set of practices for handling software changes, investigations, reviews, and design work.

Skill for Claude CodeGemini CLI

Written for Claude Code and Gemini CLI: PostToolUse hook event, but also installed under .gemini/. Also seen: mentions Claude Code; built for gstack; mentions Gemini CLI.

This is kk376/dev-suite's own configuration. It tells Claude Code and Gemini CLI how to work on dev-suite itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dev-suite configures →

not rated 0repo changed 1mo ago C scan 324 tokens original MIT
View source ↗ kk376/dev-suite
Reuse

Borrowing it

Nothing to install: this file belongs to kk376/dev-suite. 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/kk376/dev-suite/main/.gemini/config/skills/engineer/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kk376/dev-suite

Made for: Claude Code, Gemini CLI.

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.

agentmods badge for engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/kk376/dev-suite/engineer/github.svg)](https://agentmods.dev/skills/kk376/dev-suite/engineer)
Your own site
<a href="https://agentmods.dev/skills/kk376/dev-suite/engineer"><img src="https://agentmods.dev/badge/skills/kk376/dev-suite/engineer/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.

agentmods 80×15 button for engineer

Your own site · 80×15
<a href="https://agentmods.dev/skills/kk376/dev-suite/engineer"><img src="https://agentmods.dev/badge/skills/kk376/dev-suite/engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 324 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 13,262 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 3 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00324 $0.13262
Opus 5.5 $0.00130 $0.05305
Sonnet 5.5 $0.00065 $0.02652
Haiku 4.5 $0.00032 $0.01326

Measured 1mo ago against content hash 80273eda0e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

engineer scanned grade C with 3 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 1mo ago.

The scan reads SKILL.md. This mod also ships 8 executable files (scripts/arch_report.py, scripts/brand_picker.py, scripts/check_markdown_references.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reaches for credential filesmediumPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- **Mandatory SSH-Signed Commits**: All commits across all repositories must be cryptographically signed using SSH (`git commit -S`, `gpg.format = ssh`, `user.signingkey = ~/.ssh/id_ed25519.pub`). Unsigned commits or his

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- *HIGH Tier (Hard Deny)*: Unconditional block on catastrophic, unrecoverable actions (`rm -rf /`, `rm -rf ~`, `rm -rf $HOME`, force-pushes to default branches `main`/`master`).

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **CI Agent Manifest & Permission Guards**: Automate CI verification of settings manifests to ban wildcard permissions (e.g. `Bash(*)`, `Bash(curl:*)`), enforce `.gitignore` state leak protection, and ban npm lifecycle
.gemini/config/skills/engineer/SKILL.md · 373 lines

How it starts

The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Universal Master Engineering & Design Skill

A unified, production-grade standard for software engineering craftsmanship, deep system architecture, defensive zero-trust security, upstream open-source maintainer collaboration, high-performance canvas/document viewing, contract-first API design, zero-downtime database migrations, and UI/UX design excellence. Synthesizes decades of software design principles (Ousterhout, Beck, Evans, Pragmatic Programmer) with 74 real-world production design systems across 8 archetypes, the 17-category Vibe-Check defensive security standard, and high-leverage agent operating patterns from gstack and ECC Universal.

The Master Engineering & Design Lifecycle

Every feature, interface, and system follows a disciplined, traceable progression:

┌─────────────────────────────────────────────────────────────────────────────────────────┐
│                           THE UNIFIED MASTER WORKFLOW PIPELINE                          │
└─────────────────────────────────────────────────────────────────────────────────────────┘
                                           │
  1. Discovery, Council & Alignment        ▼
     [Concept / Feature] ─────► [grill-with-docs / council] ────► [design-archetype / prototype]
                                           │                                    │
                                           ├────────────────────────────────────┘
  2. Architecture, Contracts & Slicing     ▼
     [contract-first / tokens] ───────► [to-spec / spec-mine]
                                           │
                                           ▼
                                     [to-tickets] (Vertical Tracer Bullets + Blocking DAG)
                                           │
  3. Execution, TDD & De-Sloppify          ▼
     [db-migration] ──────────────────► [implement] ◄───────► [tdd] (Red-Green-Refactor)
                                           │                      │
                                           │                      ▼
                                           │             [de-sloppify] (Purge Test Slop)
                                           ▼                      │
                                 [diagnosing-bugs] ◄──────────────┘
                                           │
  4. Defensive Security & Auditing         ▼
     [security-audit / vibe-check] ───► [silent-failure] (17 Guardrails + Zero Swallowed Errors)
                                           │
  5. Review, Adversarial Gate & Polish     ▼
     [code-review] ───────────────────► [santa-review] (Independent Dual-Review Pass)
                                           │
                                           ▼
                            [improve-codebase-architecture] (Deep Modules)
                                           │
  6. CI/CD Simulation, Release & Remote    ▼
     [packaging / release] ──► [ci-simulation] ──► [signed-push] ──► [gh-ci-watch] ──► [Ship / Merge]

Read the full file on GitHub · 373 lines

Files

What ships with it

50 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.

  1. 1mo ago Changed · +11 lines · +45 tokens per session 80273eda0e69
  2. 1mo ago Changed · +7 lines b97af87a1dc3
  3. 1mo ago Changed c6f00e318d7c
  4. 1mo ago Changed · +23 lines · +47 tokens per session scan B → C 81f30e82f102
  5. 1mo ago Changed · +1 lines 1c556dcbbdf6
  6. 1mo ago Changed · +43 lines · +14 tokens per session b2a03beaa3ce
  7. 2mo ago Changed · +23 lines · +54 tokens per session 018d90a64d69
  8. 2mo ago Changed · +64 lines · +54 tokens per session scan A → B 8046101410bd
  9. 2mo ago First seen · 201 lines · 110 tokens per session scan A b19570cc7361

Subscribe to this mod's changes

engineer is a skill published in the GitHub repository kk376/dev-suite (0 stars, last pushed 28d ago), licensed MIT. It adds 324 tokens to every session and 13,262 once invoked, about $0.0013 per session on Opus 5.5. A static security scan graded it C with 3 findings (reaches for credential files, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agent-skillsdeveloper-environmentdotfilesfedorapackagingwsl2
Related

engineer compared with skills from other repositories

engineer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
engineerkk376/dev-suiteSkill028d agoMITC324Claude Code, Gemini CLI
hermes-cron-automationsAmineDjeghri/personal-os-setupSkill671yesterdayMITA19Claude Code, Codex
merge-prjoshukraine/dotfilesSkill42910d agoMITA23Claude Code
youtube-download-automationAmineDjeghri/personal-os-setupSkill671yesterdayMITB47Claude Code, Codex
bootstrap-prdjoshukraine/dotfilesSkill42910d agoMITA25Claude Code
gui-debugnatsukium/dotfilesSkill106yesterdayCC0-1.0A113Claude Code, Codex
auditdarkroomengineering/cc-settingsSkill52yesterdayMITA69Claude Code