openspec

A workflow for OpenSpec, a command-line system that records proposed software changes as reviewable specifications and task lists. It covers exploring an idea, proposing and applying changes, syncing specifications, and archiving completed work.

In plain words
What is it for?
Use it to investigate a change, write its proposal and design, implement listed tasks, update the main specifications, and finish the change record.
Why use it?
It keeps the reasoning, design, requirements, and implementation tasks for a change organized across sessions.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/jonnyton/tinyassets/openspec
Any agent
npx skills add Jonnyton/TinyAssets --skill openspec
Clone the repo
git clone --depth 1 https://github.com/Jonnyton/TinyAssets

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.01382
Opus 5 $0.00031 $0.00691
Sonnet 5 $0.00012 $0.00276
Haiku 4.5 $0.00006 $0.00138

Measured yesterday against content hash 50e2e2a08725, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.agents/skills/openspec/SKILL.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenSpec

Requires the openspec CLI (MIT, Fission-AI/OpenSpec; npm i -g @fission-ai/openspec). Specs live in the repo and persist across sessions. This is the CLI-managed, multi-session spec system. Where the CLI is unavailable, hand-write a change directory matching the OpenSpec layout (proposal.md, design.md, delta specs, tasks.md) so it can be adopted once the CLI is back — see AGENTS.md § Spec-driven development.

Lifecycle

explore → propose → apply → sync-specs → archive
(think)   (artifacts) (build) (merge deltas) (finalize)

Each is an action on a change, not a rigid phase — invoke any of them anytime. Always orient first with openspec list --json (active changes) and openspec status --change "<name>" --json (schema, paths via planningHome / changeRoot / artifactPaths / actionContext). Use those resolved paths — never assume repo-local paths. If status reports actionContext.mode: "workspace-planning" with empty allowedEditRoots, that operation isn't supported in this slice — treat linked repos/folders as read-only and STOP before editing.

At dispatch/triage time, also run python scripts/openspec_flow.py audit and finish existing delivery WIP before admitting more. This is on-demand flow control, not a mandatory session-start step.

explore — a thinking partner

A stance, not a workflow: curious, visual (ASCII diagrams liberally), adaptive, grounded in the actual codebase. Never write code or implement features in explore mode — you may read/search/investigate and create OpenSpec artifacts (that's capturing thinking), but if asked to implement, tell the user to exit explore and create a proposal. Offer to capture crystallized insights into the right artifact (requirement → specs, design decision → design.md, scope → proposal.md, new work → tasks.md); the user decides — don't auto-capture.

propose — generate all artifacts

Create a change and its artifacts in one pass. Derive a kebab-case name from the user's description (don't proceed without understanding what they want): openspec new change "<name>"openspec status --change "<name>" --json for the build order (applyRequires, artifacts with dependencies). Loop through ready artifacts in dependency order: openspec instructions <artifact-id> --change "<name>" --json gives template (structure to write), resolvedOutputPath, and context/rules (constraints for YOU — never copy these blocks into the file). Read completed dependencies for context, write each artifact, re-check status, until every applyRequires artifact is done. Verify each file exists before moving on.

Read the full file on GitHub · 106 lines

Changes

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.

  1. yesterday First seen · 106 lines · 62 tokens per session scan A 50e2e2a08725

Subscribe to this mod's changes

openspec is a skill published in the GitHub repository Jonnyton/TinyAssets (1 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,382 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens