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 skills add znlgis/my-opencode-deepseek-config --skill spec-workflowgit clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-configWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/spec-workflow)<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/spec-workflow"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/spec-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/spec-workflow"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/spec-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00104 | $0.01554 |
| Opus 5.5 | $0.00042 | $0.00622 |
| Sonnet 5.5 | $0.00021 | $0.00311 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
spec-workflow 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec-Driven Change Workflow
Plan and land a change through durable, git-tracked artifacts shared by humans and coding agents. Adapted (pure prompt, no tooling) from OpenSpec OPSX.
Philosophy
- Enablers, not gates. Artifacts show what's possible next, not what you MUST do — edit an earlier artifact anytime.
- Artifacts are the source of truth. Plans live as markdown in the repo, so they survive the session and stay greppable.
- Brownfield-friendly + scale down. Delta specs (ADDED/MODIFIED/REMOVED/RENAMED) describe only what changes; skip the ceremony for a one-line fix.
Directory convention
openspec/
├── specs/<capability>/spec.md ← source of truth (shipped behavior)
├── explorations/<topic>.md ← optional pre-proposal notes
└── changes/
├── <change-id>/ ← one in-flight change (kebab-case)
│ ├── proposal.md ← WHY + WHAT (required)
│ ├── design.md ← HOW (optional, only when warranted)
│ ├── tasks.md ← checklist the apply step tracks (required)
│ └── specs/<capability>/spec.md ← delta: what this change adds/edits
└── archive/YYYY-MM-DD-<change-id>/ ← completed changes, kept for history
Project-wide context and rules live in AGENTS.md — honor it in every artifact.
Action: propose
Create openspec/changes/<change-id>/ with a proposal, tasks, delta specs, and
(when warranted) a design. Research existing code and openspec/specs/ first.
- proposal.md (1–2 pages, WHY not HOW):
## Why,## What Changes(mark BREAKING),## Capabilities,## Impact, an initially-empty## Updates. - tasks.md:
- [ ]checkboxes, grouped and ordered by dependency; each task fits one session and states its observable done-condition in the checkbox text (the verification that must pass to mark it[x]). - design.md: only if cross-cutting, a new pattern/dependency/data-model, or security/performance/migration complexity (Context · Goals/Non-Goals · Decisions · Risks · Migration · Open Questions).
- skip_specs — a pure refactor, tooling, or docs change with no observable
behavior change needs no spec contract. Set
skip_specs: trueinproposal.mdand omit delta specs; the tasks checklist still carries its own done-conditions.
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.
- 1mo ago Changed · +5 lines e115469d092b
- 1mo ago First seen · 121 lines · 104 tokens per session scan A d41f34658f38
spec-workflow is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (59 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 1,554 once invoked, about $0.0004 per session on Opus 5.5. 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
my-opencode-deepseek-config
Use when deploying, tuning, or extending the OpenCode × DeepSeek V4 optimal configuration (orchestrator routing, 12 agents, thinking tiers, prompt-cache prefix discipline, limit.input compaction windows, permissions baseline, 23 skills, slash commands) — installing to another machine, adding an agent or skill…
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
image-generator
Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.