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 intent-driven-dev/openspec-schemas --skill openspec-linearizedgit clone --depth 1 https://github.com/intent-driven-dev/openspec-schemasWrote 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/intent-driven-dev/openspec-schemas/openspec-linearized)<a href="https://agentmods.dev/skills/intent-driven-dev/openspec-schemas/openspec-linearized"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/openspec-schemas/openspec-linearized/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/intent-driven-dev/openspec-schemas/openspec-linearized"><img src="https://agentmods.dev/badge/skills/intent-driven-dev/openspec-schemas/openspec-linearized.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 | $0.00101 | $0.01465 |
| Opus 5.5 | $0.00040 | $0.00586 |
| Sonnet 5.5 | $0.00020 | $0.00293 |
| Haiku 4.5 | $0.00010 | $0.00146 |
Grade A, and why
openspec-linearized 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenSpec Linearized
Use this skill to run an OpenSpec change lifecycle while preserving a clear handoff boundary:
- Linear issue/card owns the business "what": business goal, use cases, personas/workflows, scope, acceptance criteria, and stakeholder-facing status. Keep its description synchronized from the business-facing content in
proposal.md. - The repo owns the technical "how": OpenSpec design decisions, tasks, implementation details, migrations, tests, and code.
- Canonical specs live under
openspec/specs/. After archive succeeds, mirror those specs into Linear Project Documents for stakeholder visibility.
Linear updates are best effort once project setup exists.
Invocation Contract
- If the user asks to operate on an OpenSpec change, use this skill as the Linear lifecycle overlay.
- Also use the base OpenSpec skill that matches the request, such as
openspec-propose,openspec-apply-change,openspec-archive-change, oropenspec-sync-specs. - If
openspec/linear.yamlexists, run the relevant Linear hook for the current phase when possible. - If
openspec/linear.yamlis missing during proposal/setup, create it before issue hunting, story selection, or other Linear lifecycle work. - If
openspec/linear.yamlis missing outside proposal/setup, no-op the Linear hook and continue normal OpenSpec work. - For status, validate, sync, continue, and artifact-editing work, preserve Linear binding awareness but do not move a Linear story to Done.
Start
- Read
references/lifecycle.mdbefore doing lifecycle work. - Run
openspec list --jsonto understand active changes. - Determine the phase from the request:
- Proposal: create or continue an OpenSpec change and bind a Linear story.
- Apply: implement
tasks.mdwhile updating the bound Linear story. - Archive: archive the OpenSpec change, then mirror canonical specs and close the story.
- Sync/status/validate/continue/artifact work: keep the Linear binding in view, preserve the ownership boundary, and avoid Done transitions.
- If another OpenSpec skill also applies, use this skill as the Linear lifecycle overlay and follow the base OpenSpec skill for normal artifact generation, task execution, or archive mechanics.
What ships with it
2 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.
- 1mo ago First seen · 83 lines · 101 tokens per session scan A a9f8ab5b2953
openspec-linearized is a skill published in the GitHub repository intent-driven-dev/openspec-schemas (110 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 1,465 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 2026-09-03.
Other skills, from other repositories
spec-manager
Spec-driven project iteration workflow: L1 PRD -> L2 Design -> L3 Impl -> Agent Task, with human review gates at each layer.
specd-archive-change
Encerra uma change do specd — confere gate verde, anuncia a escrita, aplica o delta em .specd/specs/ com specd archive e, havendo board, sincroniza e transiciona os itens da change. Use quando o usuário quiser finalizar, arquivar ou encerrar uma change já implementada.
specd-explore
Abre uma change do specd e explora o que ela vai encostar — escopo, mapa do código, requisitos existentes, lacunas — gravando o resultado em explore/notes.md e, havendo board, coletando o card com specd explore. Use quando o usuário quiser começar uma mudança, investigar antes de propor, ou entender o que já existe…
gsd-map-codebase
Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents.
gsd-manager
Interactive command center for managing multiple phases from one terminal.
gsd-new-project
Initialize a new project with deep context gathering and PROJECT.md.