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.
npx agentmods add skills/devnomad-byte/techneering/draftnpx skills add devnomad-byte/techneering --skill draftgit clone --depth 1 https://github.com/devnomad-byte/techneeringWhat 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 | $0.00043 | $0.01952 |
| Opus 5 | $0.00022 | $0.00976 |
| Sonnet 5 | $0.00009 | $0.00390 |
| Haiku 4.5 | $0.00004 | $0.00195 |
Grade A, and why
draft 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft a Change
Create a complete Techneering change — generate all specification artifacts in one step. Read project context and spark conclusions (if any), then produce: proposal → specs → design → tasks.
Core Principle
UNDERSTAND BEFORE BUILDING.
Do NOT proceed without understanding what the user wants to build.
Steps
Step 1: Understand the Request
If the user's request is unclear, ask what they want to build. Derive a kebab-case name (e.g., "add user authentication" → add-user-auth).
If spark conclusions exist in the conversation, read them as input.
Step 2: Initialize Project Workspace (First Time Only)
Check if techneering/ directory exists at the project root. If not, create:
techneering/
├── config.yaml # project context and rules
├── specs/ # main specification docs
├── changes/ # active changes
└── archive/ # archived changes
Generate config.yaml:
schema: spec-driven
context: |
# TODO: fill in project context (tech stack, framework, database, deployment environment, etc.)
coding_conventions:
naming:
files: "" # kebab-case / PascalCase / camelCase / snake_case
classes: "" # PascalCase (Java/TS class) / snake_case (Ruby/Python)
functions: "" # camelCase / snake_case / PascalCase
constants: "" # UPPER_SNAKE / camelCase / PascalCase
variables: "" # camelCase / snake_case
structure:
pattern: "" # feature-based / layered / mvc / modular / monorepo / hexagonal
source_dir: "" # src/ / lib/ / app/ / internal/
test_dir: "" # tests/ / __tests__/ / test/ / src/test/
patterns:
error_handling: "" # exceptions / Result type / error codes / try-catch
dependency_injection: "" # constructor / annotations / manual / module system
api_style: "" # REST / GraphQL / gRPC / message-queue
data_access: "" # ORM / query-builder / raw-sql / repository-pattern
imports: "" # alias / relative / absolute / package-based
formatting:
indent: "" # 2 spaces / 4 spaces / tab
quotes: "" # single / double
semicolons: "" # true / false
trailing_comma: "" # es5 / all / none
max_line_length: "" # 80 / 100 / 120 / none
quality_standards:
# standard sources (stackable, ordered by priority)
sources:
- "" # primary standard source (see options table below)
# custom rules (override or supplement the sources)
custom_rules: []
# review severity level
severity: "strict" # strict (Critical must fix) / normal (Important should fix) / relaxed (inform only)
rules:
proposal: []
specs: []
design: []
tasks: []
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.
- yesterday First seen · 210 lines · 43 tokens per session scan A c62cc40ab7a9
draft is a skill published in the GitHub repository devnomad-byte/techneering (13 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,952 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
workflows
Execute a workflow script that orchestrates multiple subagents deterministically. Use when the user explicitly requests a workflow, multi-agent orchestration, parallel or sequential agent pipelines, structured agent outputs, or a durable background workflow run.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
regex-mastery
Use this skill when writing regular expressions, debugging pattern matching,optimizing regex performance, or implementing text validation. Triggers on regex, regular expressions, pattern matching, lookahead, lookbehind, named groups, capture groups, backreferences, and any task requiring text pattern matching.
office-hours
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…