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/assemblenpx skills add devnomad-byte/techneering --skill assemblegit 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 | $0.00014 | $0.00981 |
| Opus 5 | $0.00007 | $0.00491 |
| Sonnet 5 | $0.00003 | $0.00196 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
assemble 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assemble: Subagent-Driven Execution
Execute plans by dispatching a fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
Core Principle
FRESH SUBAGENT PER TASK + TWO-STAGE REVIEW = HIGH QUALITY.
Never skip reviews. Never reuse context between tasks.
Model Selection
Use the least powerful model that can handle each role:
- Mechanical tasks (1-2 files, clear specs): fast/cheap model
- Integration tasks (multi-file, debugging): standard model
- Architecture/review tasks: most capable model
Steps
Step 1: Read Plan and Extract Tasks
Read the implementation plan. Extract all tasks and create a todo list.
Step 2: Execute Tasks (Per-Task Loop)
For each task:
2a. Dispatch Implementer Subagent
Frontend Detection: Before dispatching, check if the task involves frontend/UI work. Match against the Frontend Detection Rules in tn:compass (keywords: page/component/UI/layout/style/React/Vue/CSS/Tailwind/form/button/animation etc.). If matched, invoke tn:craft first to get aesthetic guidance, then include that guidance in the implementer prompt.
Use ./implementer-prompt.md template. Provide full task text (never make subagent read the plan file).
One commit per task: the implementer commits its own work before returning (the review stages below compare that commit's diff). Each task = one commit, so 2b/2c reviews have a clean BASE_SHA→HEAD_SHA range per task.
Handle status:
- DONE: Proceed to spec compliance review
- DONE_WITH_CONCERNS: Read concerns, address if needed, proceed
- NEEDS_CONTEXT: Provide missing context and re-dispatch
- BLOCKED: Assess blocker, provide context or re-dispatch with better model
Never ignore an escalation or force the same model to retry without changes.
2b. Dispatch Spec Reviewer Subagent
Use ./spec-reviewer-prompt.md template. Verify implementer built what was requested (nothing more, nothing less).
What ships with it
3 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.
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.
- 2d ago First seen · 110 lines · 14 tokens per session scan A 69467d41f615
assemble is a skill published in the GitHub repository devnomad-byte/techneering (13 stars, last pushed 2mo ago), licensed MIT. It adds 14 tokens to every session and 981 once invoked, about $0.0001 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…