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/heiko-braun/draft/implementnpx skills add heiko-braun/draft --skill implementgit clone --depth 1 https://github.com/heiko-braun/draftWhat 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 | $0.00027 | $0.00846 |
| Opus 5 | $0.00014 | $0.00423 |
| Sonnet 5 | $0.00005 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
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 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation
You implement features as small, complete vertical slices with continuous testing.
When to Activate
- After the spec skill has created and confirmed a specification
- When user says "implement" and a spec file exists
- When user explicitly references a spec file
Workflow
1. Load Spec & Search for Context
Read the relevant /specs/{feature}.md file. If multiple specs exist and it's unclear which one, ask the user.
Search for related code: Before writing any code, use the spec's title and key terms to search the codebase for relevant existing code:
draft search "<spec title and key terms>" --limit 10
Review the search results to understand existing patterns, related modules, and potential conflicts. Use these results to inform your implementation approach.
Before writing any code, assess the change:
- Which modules/files will this touch? List them. If the spec has an "Affected Modules" section, verify it's still accurate.
- Are we modifying shared code? Changing a shared utility, interface, or base class affects every consumer. Flag this to the user.
- Can we contain the change? Prefer adding new files/functions over modifying widely-imported ones. Prefer narrow interfaces that isolate the new behaviour from the rest of the codebase.
- Are we adding new dependencies? Each dependency is a coupling point. Avoid unless clearly justified.
If the blast radius is wider than expected, flag it: "This will touch N modules beyond what the spec anticipated. Want to proceed or restructure?"
2. Implement
Implement the spec as one integrated piece — types, logic, wiring, and tests together. A small vertical slice doesn't need artificial separation into "foundation" and "core logic" and "integration" phases.
Use TodoWrite to track progress against the spec's acceptance criteria.
Design for modularity as you go:
- Place new behaviour behind clear interfaces — functions, types, modules — so callers don't depend on implementation details.
- Avoid reaching into the internals of other modules. If you need something, use or extend its public interface.
- Keep new files/functions narrowly focused. One responsibility per unit.
- If a change to shared code is unavoidable, make the interface change first, verify existing tests still pass, then build the new behaviour on top.
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 · 93 lines · 27 tokens per session scan A 752769689069
implement is a skill published in the GitHub repository heiko-braun/draft (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 846 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…