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/davepoon/buildwithclaude/implement-featurenpx skills add davepoon/buildwithclaude --skill implement-featuregit clone --depth 1 https://github.com/davepoon/buildwithclaudeWhat 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 | $0.00034 | $0.00360 |
| Opus 5 | $0.00017 | $0.00180 |
| Sonnet 5 | $0.00007 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
implement-feature 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 3d 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.
What it actually says
Implement Feature
Implements a feature from its specification using the Forja (Dev) agent.
When to Use This Skill
- A feature spec has been approved and is ready for implementation
- You need architecture design, code, and tests for a defined feature
- Translating product requirements into working software
What This Skill Does
- Runs the SIGN IN checklist and verifies the spec handoff
- Designs architecture (creates ADR if needed)
- Defines interfaces/contracts, then implements in
src/ - Writes tests in
tests/(unit + integration) - Runs the Implementation Complete checklist (TIME OUT 1)
- Runs the Pre-Delivery checklist (TIME OUT 2)
- Prepares structured handoff to QA agent
- Runs the SIGN OUT checklist
How to Use
Basic Usage
/implement-feature webhook-event-system
With Spec Reference
/implement-feature docs/specs/webhook-event-system.md
Example
User: /implement-feature user-authentication
Output:
- Implementation in
src/with all acceptance criteria met - Tests in
tests/covering critical paths - ADR if significant architecture decisions were made
- Handoff notes for QA: files changed, how to test, known limitations
Tips
- Ensure the feature spec exists before running this skill
- The agent creates an ADR for any significant architecture decisions
- Two TIME OUT checkpoints ensure both correctness and delivery cleanliness
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.
- 3d ago First seen · 57 lines · 34 tokens per session scan A 843bf4b5799a
implement-feature is a skill published in the GitHub repository davepoon/buildwithclaude (3,405 stars, last pushed 3d ago), licensed MIT. It adds 34 tokens to every session and 360 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
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE…
aidd-refine:03:condense
Toggle terse output mode with intensity levels (lite, full, ultra) so prose drops articles, filler, and pleasantries while code, quoted errors, and security warnings stay verbatim. Use when the user says "condense", "condense output", "be more concise", "shorter answers", "tighten output", "/condense", "/condense…
aidd-pm:04:clarity
Ultra-compressed communication mode. Cuts token usage 75% while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra. Toggle on/off by invoking /clarity again. Use when user says "clarity", "less tokens", "be brief", or invokes /clarity.
meeting-prep
Pre-meeting context gathering across all connected systems. Pulls recent interactions, open items, and suggested talking points for any person or topic. Triggers on: "meeting prep", "prep for my meeting", "meeting with X", "prep for 1:1".
codexspec:release-notes
从 git 历史生成发布说明——维护 Keep a Changelog 风格的 CHANGELOG.md 条目并产出面向用户的发布正文，不决定版本号、不改动 git 状态.
turnbreak
Shows you something worth reading while your coding agent works, then notifies you when it's done. Use this skill to install turnbreak's turn-start/turn-stop hooks for Claude Code, Codex, Gemini CLI, or Copilot CLI, or to manage its interests and settings.