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 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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00084 | $0.00992 |
| Opus 5.5 | $0.00034 | $0.00397 |
| Sonnet 5.5 | $0.00017 | $0.00198 |
| Haiku 4.5 | $0.00008 | $0.00099 |
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 1mo 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⛔ GATE DISCIPLINE: host user-choice mechanism gates = hard stops. Never skip or auto-pick answer. Tool unavailable → numbered-text fallback → stop, wait for reply. No flag bypasses a gate; override flags pass only as user's recorded gate answer.
/tech-implement
Release version: 2.0.0
Deliver cohesive milestones with evidence, not a fresh dispatch per checkbox.
Routing
| Intent | Route |
|---|---|
| Plan/spec or feature to execute | workflows/execute-plan.md |
| Bug or failed test to fix | workflows/fix-bug.md |
| Diagnosis only | workflows/systematic-debugging.md, no repair authority |
| Finish existing work | workflows/finish-branch.md |
Ambiguous intent → a structured choice prompt ⛔ BLOCKING: Execute a plan / Fix a bug / Finish in-progress branch. Fallback: numbered options in plain text; stop and wait.
Operating contract
- Before action ⛔ BLOCKING: load
shared/technical-delivery-doctrine.md,references/runtime-adapter.md, owning repository instructions and selected workflow. - Controller binds milestone goal/non-goals, approved constraints, proof, dependencies, exact ownership and escalation. Legacy plans remain accepted; preserve user-approved constraints, not automatic authority for historical microsteps.
- Worker plans locally and retains context through cohesive test-first cycles. Authorized read-only diagnosis may precede test writing; changed behaviour requires observed discriminating RED before production behaviour changes, then GREEN; refactor-only uses characterization baseline and regressions.
references/adaptive-tdd-protocol.mdapplies to every capability tier. - Scope independent review to changed risks/contracts, affected consumers and final integration: spec first, quality second, controller verification last. Group cohesive milestones rather than repeat review per checkbox. Identical snapshot/scope reuse follows shared doctrine; final integrated result must be covered by both reviews. Missing independent reviewer blocks completion, not an invitation to relabel self-review.
- Close only after all acceptance outcomes have fresh evidence against final files. Use finish route for exact user choice and documentation close-out.
What ships with it
20 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 3.6 KB
- agents/quality-reviewer.md 2.4 KB
- agents/spec-reviewer.md 2.4 KB
- PORTABILITY.md 2.9 KB
- references/adaptive-tdd-protocol.md 3.2 KB
- references/runtime-adapter.md 344 B
- references/status-code-handling.md 3.4 KB
- references/tdd-protocol.md 4.1 KB
- references/verification-protocol.md 2.1 KB
- references/worktree-setup.md 4.9 KB
- shared/code-organization.md 6.6 KB
- shared/technical-delivery-doctrine.md 9.5 KB
- shared/technical-delivery-runtime-adapter.md 6.3 KB
- shared/technical-delivery-test-level.md 3.4 KB
- shared/test-level-protocol.md 3.4 KB
- tech-implement-readme.md 4.9 KB
- workflows/execute-plan.md 4.8 KB
- workflows/finish-branch.md 3.5 KB
- workflows/fix-bug.md 2.1 KB
- workflows/systematic-debugging.md 2.4 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.
- 1mo ago Changed · -59 lines · +6 tokens per session 1668ea96e912
- 1mo 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 1mo ago), licensed MIT. It adds 84 tokens to every session and 992 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
engram-testing-coverage
TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.
principle-test-behavior-not-implementation
Apply when you write, change, or keep a test. Assert what the code's users can observe, so that the test fails when that behavior breaks and keeps passing when only the internals change.
conductor-implement
Execute tasks from a track's implementation plan following TDD workflow.
tdd
This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…
mobiai-mobile-tdd
You MUST use this before writing any implementation code for a mobile feature, bug fix, refactor, or behavior change. Tests come before implementation — no exceptions.
iterative-development
TDD iteration loops using Claude Code Stop hooks - runs tests after each response, feeds failures back automatically.