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/itechmeat/llm-code/openspecnpx skills add itechmeat/llm-code --skill openspecgit clone --depth 1 https://github.com/itechmeat/llm-codeWhat 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 | $0.00062 | $0.01289 |
| Opus 5 | $0.00031 | $0.00645 |
| Sonnet 5 | $0.00012 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
openspec 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 2d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec (OPSX) Skill
Use this skill to guide or reason about the OpenSpec artifact-driven workflow system (OPSX), including artifact graphs, schema/template resolution, change lifecycle, and experimental commands/skills.
Quick Navigation
- Artifact graph core concepts: references/artifact-core.md
- OPSX workflow behavior and usage: references/opsx-workflow.md
- Setup + profiles (init, update, config profile): references/setup-profiles.md
- Schema customization workflow and gaps: references/schema-customization.md
- End-to-end schema workflow gaps and proposed solution: references/schema-workflow-gaps.md
- Experimental release plan and rollout checklist: references/experimental-release-plan.md
Release Highlights (1.2.0 → 1.3.0)
- More tool integrations: adds support for Junie, Lingma, ForgeCode, and IBM Bob.
- Safer setup: shell completion installation is now opt-in, and Copilot auto-detection no longer triggers from a bare
.github/directory alone. - Adapter fixes: Pi command generation was corrected, and OpenCode now uses the canonical
.opencode/commands/path. - Safer status checks:
openspec statusnow exits cleanly when a project has no changes yet.
OPSX Commands
| Command | Purpose |
|---|---|
/opsx:explore |
Think through ideas, investigate problems (no structure) |
/opsx:new |
Start a new change |
/opsx:continue |
Create next artifact based on dependencies |
/opsx:ff |
Fast-forward — create all planning artifacts at once |
/opsx:apply |
Implement tasks, updating artifacts as needed |
/opsx:verify |
Validate implementation matches spec |
/opsx:sync |
Sync delta specs to main specs |
/opsx:archive |
Archive single completed change |
/opsx:bulk-archive |
Archive multiple completed changes at once |
What ships with it
6 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.
- 2d ago First seen · 142 lines · 62 tokens per session scan A 30660c382337
openspec is a skill published in the GitHub repository itechmeat/llm-code (22 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 1,289 once invoked, about $0.0003 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
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…