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/bitcraft-apps/spec-first/implementnpx skills add bitcraft-apps/spec-first --skill implementgit clone --depth 1 https://github.com/bitcraft-apps/spec-firstWhat 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 | $0.00006 | $0.00604 |
| Opus 5 | $0.00003 | $0.00302 |
| Sonnet 5 | $0.00001 | $0.00121 |
| Haiku 4.5 | $0.00001 | $0.00060 |
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Command
Creates a minimal implementation that follows the existing patterns. One agent does the steps in order.
Usage
/sf:implement [--isolate] [SPECIFICATION_OR_PATH]
Context
Read the current branch. Check whether .sf/spec.md exists.
Input Resolution
- If the skill has arguments: use them as a specification path or as inline requirements
- Else if
.sf/spec.mdexists: use it - Else: ask the user where the specification is. Wait for the answer.
Execution
Step 1 — Learn
- Search the codebase for the closest existing pattern for this specification. Stop when you have one good example. Do not survey the whole repository.
- Write the example to
.sf/research/pattern-example.md.
Step 2 — Implement
- Follow the pattern you found. No creativity.
- Write the simplest change that works. No abstractions for later. One feature at a time.
- Test that it works.
- Write
.sf/implementation-summary.md.
Gate — Post-Implementation: run scripts/validate-implementation.sh, in this skill directory.
If validate-implementation.sh fails (non-zero exit), check every criterion the spec meets, or
finish the work it names. Do not report the implementation as done.
Output: Implementation + .sf/implementation-summary.md
If Step 1 finds no pattern: create the basic file structure the language expects, implement only the core requirement, and note in the summary: "No existing patterns found - used minimal approach".
Philosophy
This command enforces:
- Pattern consistency over creativity
- Working code over perfect code
- Minimal solution over extensible solution
On Claude Code
Claude Code has subagents. Use them for both steps.
Context arrives for free:
-
Branch: !
git branch --show-current 2>/dev/null -
Spec exists: !
test -f .sf/spec.md && echo "yes" || echo "no" -
Parse $ARGUMENTS.
--isolateis a Claude-only flag: strip it and set ISOLATE=true. -
Use the AskUserQuestion tool to ask for the specification location.
-
Step 1: use the Agent tool with subagent_type="Explore" to find the pattern for $SPECIFICATION (request "medium" thoroughness in the prompt).
-
Step 2: Task: implement-minimal with spec: $SPECIFICATION. If ISOLATE is true, add isolation: "worktree".
-
Gate:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/validate-implementation.sh ${CLAUDE_PROJECT_DIR:+$CLAUDE_PROJECT_DIR/.sf}
What ships with it
1 file 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.
- yesterday First seen · 72 lines · 6 tokens per session scan A 3cc03fa337bd
implement is a skill published in the GitHub repository bitcraft-apps/spec-first (4 stars, last pushed 4d ago), licensed MIT. It adds 6 tokens to every session and 604 once invoked, about $0.0000 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
anti-slop-design
Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…
3d-web-experiences
Build distinctive, performant, production-grade 3D on the web with Three.js, React Three Fiber, and WebGL. Use when the user asks to "build a 3D scene", "add a 3D hero/landing", "make a product viewer/configurator", mentions three.js / react-three-fiber / r3f / drei / webgl / shaders, or asks to make an existing 3D…
deep-research
Conducts multi-step deep research on any topic using iterative search, reflection, and synthesis. Use when the user asks to research, investigate, survey, compare, analyze, deep-dive, or explore a topic in depth. Covers web research, codebase analysis, documentation review, mixed-source investigation, and M3…
minimax-m3-long-context
How to use MiniMax M3's 1M-token MSA context productively: what to load vs. compress, when to retrieve vs. ingest, how to keep skills shallow in the always-on prompt and deep in skills, and how to plan retention across iterations. Load when the task might exceed 200K tokens, when the user asks to "keep all of this in…
minimax-m3-multimodal-input
How to use MiniMax M3's native multimodal input (image, video) for grounded decisions in coding work. Covers reading attached images/frames, treating them as ground truth for visual claims, screenshot diffing, design parity from mockups, and routing visual evidence through reports and PRs. Load when the user attaches…
minimax-multimodal-toolkit
MiniMax-native multimodal workflow for image, video, voice, music, and media-processing tasks. Use when the user asks to generate image/video/audio assets, wants MiniMax-specific media APIs, needs TTS or voice workflows, wants reproducible local media outputs, or needs FFmpeg-style processing around generated media.…