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/nanparth/ai-skill-hub/tech-implementnpx skills add nanparth/ai-skill-hub --skill tech-implementgit clone --depth 1 https://github.com/nanparth/ai-skill-hubWrote 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.
[](https://agentmods.dev/skills/nanparth/ai-skill-hub/tech-implement)<a href="https://agentmods.dev/skills/nanparth/ai-skill-hub/tech-implement"><img src="https://agentmods.dev/badge/skills/nanparth/ai-skill-hub/tech-implement.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00078 | $0.01229 |
| Opus 5 | $0.00039 | $0.00615 |
| Sonnet 5 | $0.00016 | $0.00246 |
| Haiku 4.5 | $0.00008 | $0.00123 |
Grade A, and why
tech-implement 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 4d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tech-implement
Execute implementation plans or bug fixes with TDD, isolated work, subagent review, and verification gates.
Required Dependencies
- Git.
- Shell access.
- A runnable project test command such as
pytest,npm test,cargo test, or a user-provided command. - Subagent support for the full pipeline. Without subagents, follow the checklists manually and do one task at a time.
Optional: GitHub CLI (gh) for pull request creation. If gh is unavailable, push the branch manually or provide PR instructions instead.
Routing
| Intent | Action |
|---|---|
User has a plan file or tech-blueprinting output to execute |
Load workflows/execute-plan.md |
| User reports a bug or test failure needing a fix | Load workflows/fix-bug.md |
| User wants systematic debugging without committing to a fix | Load workflows/systematic-debugging.md |
| User wants to finish a branch already in progress | Load workflows/finish-branch.md |
If intent is ambiguous, ask whether this is a plan to execute, a bug to fix, or in-progress work to finish.
Pipeline Overview
Feature from plan:
plan -> task extraction -> worktree -> per-task loop -> final review -> finish -> optional docs
Per-task loop:
implementer subagent -> spec reviewer -> quality reviewer -> verification gate -> mark complete
Bug fix:
bug report -> worktree -> systematic debugging -> synthetic task -> per-task loop -> finish
Core Principles
- Agents receive full task text inline. They do not read the plan file.
- Fresh subagent per task. No conversation context is inherited.
- TDD is mandatory. No production code without a failing test first.
- Two-stage review is mandatory: spec compliance first, code quality second.
- Verification is a gate. Run commands, read output, and check exit codes before claiming completion.
- Implementer dispatches are sequential only.
- Worktree isolation is the default for normal Git repositories.
- One responsibility per module. Use explicit interfaces.
What ships with it
15 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.
- agents/implementer.md 6.4 KB
- agents/quality-reviewer.md 4.2 KB
- agents/spec-reviewer.md 3.3 KB
- PORTABILITY.md 1.2 KB
- references/status-code-handling.md 2.4 KB
- references/tdd-protocol.md 4.4 KB
- references/verification-protocol.md 3.4 KB
- references/worktree-setup.md 2.0 KB
- shared/code-organization.md 2.5 KB
- shared/test-level-protocol.md 1.9 KB
- tech-implement-readme.md 4.7 KB
- workflows/execute-plan.md 4.2 KB
- workflows/finish-branch.md 2.3 KB
- workflows/fix-bug.md 2.5 KB
- workflows/systematic-debugging.md 6.3 KB
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.
- 4d ago First seen · 115 lines · 78 tokens per session scan A 4fd1fffa1eff
tech-implement is a skill published in the GitHub repository nanparth/ai-skill-hub (23 stars, last pushed 12d ago), licensed MIT. It adds 78 tokens to every session and 1,229 once invoked, about $0.0004 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
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
agentic-testing
MANDATORY before creating, editing, or reviewing tests in agentic.nvim, and before behavior changes that require TDD. Covers mini.test workflow, red/green rules, commands, mark-count checks, and which test references to load.
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
tdd
Test-driven development (TDD) process used when writing code. Use whenever you are adding any new code, unless the user explicitly asks to skip TDD or the code is exploratory/spike.
growing-outside-in-systems
Drive feature development using Outside-In TDD with Hexagonal Architecture. Design emerges through inline code, in-memory fakes, interface extraction, and deferred I/O. Use when building features, writing tests, or structuring backend services. Triggers on: TDD, outside-in, hexagonal, ports and adapters, emergent…
plan-create
Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…