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/specnpx skills add bitcraft-apps/spec-first --skill specgit 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 | $0.00799 |
| Opus 5 | $0.00003 | $0.00400 |
| Sonnet 5 | $0.00001 | $0.00160 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
spec 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Command
Creates a specification from requirements. One agent does the steps in order.
Usage
/sf:spec [REQUIREMENTS]
Context
Read the current branch, the last 5 commits, and the working tree.
Check whether .sf/spec.md exists.
Clarification Check
If the requirements are vague (fewer than 15 words, or unclear), ask the user before you start. Wait for the answer. Do not assume. Ask about:
- What specific problem are you solving?
- Who are the users?
- What's the desired outcome?
- Any technical constraints?
- What's the minimal viable version?
Directory Management
The working directory is .sf/. $SF_DIR overrides it.
Pick the mode:
- No
.sf/spec.md→first .sf/spec.mdexists → ask the user: "Update existing" / "Create new" →update/new
Run scripts/spec-dir.sh <first|update|new>, in this skill directory.
If spec-dir.sh fails (non-zero exit), halt immediately — do not do the work below.
Execution
Write each file in turn. The requirements are the input to this skill.
.sf/research/scope.md— the narrowest viable change. Exclude what is not needed now..sf/research/criteria.md— the simplest testable pass/fail conditions..sf/research/risks.md— blockers only, not every possible risk.$SF_DIR/spec.md— merge the three files. Keep it under 50 lines. Use the structure inspec-template.md, next to this file.
Gate — Post-Spec: run scripts/validate-spec.sh, in this skill directory.
If it fails (non-zero exit), add the sections it names, then run it again. Do not report done.
Output: $SF_DIR/spec.md (direct file or symlink to timestamped spec)
Say: "Spec written to {output path}. Run /sf:implement to build it."
On Claude Code
Claude Code runs one schema-checked combined research call by default, then synthesis. The
combined result supplies scope, criteria, and risks without research files. Set
parallelResearch: true in the workflow input to run steps 1 to 3 as three parallel research
calls.
What ships with it
3 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.
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 · 80 lines · 6 tokens per session scan A fe2aedcd03e6
spec 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 799 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.…