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/soju06/codex-lb/openspec-context-docsnpx skills add Soju06/codex-lb --skill openspec-context-docsgit clone --depth 1 https://github.com/Soju06/codex-lbWhat 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 | $0.00052 | $0.00446 |
| Opus 5 | $0.00026 | $0.00223 |
| Sonnet 5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
openspec-context-docs 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.
What it actually says
OpenSpec Context Docs
When to use
- Writing or updating OpenSpec documentation (specs, onboarding, guide, change artifacts).
- A spec is complete but readers lack background, rationale, examples, or operational notes.
- You need to preserve rich context without weakening SSOT.
Core rule: two-layer docs
spec.md= normative, testable requirements (SHALL/MUST + scenarios).- Context docs = narrative and operational detail that helps humans understand and apply the spec.
Locations
- Main specs:
openspec/specs/<capability>/spec.md(requirements)openspec/specs/<capability>/context.md(preferred)
- Optional split (if context grows):
overview.md,rationale.md,examples.md,ops.mdinside the same capability folder.
- Change-level notes (working context):
openspec/changes/<change>/context.mdornotes.md
Detail prompts (add depth without forcing a template)
Include at least 4 of these in context docs:
- Purpose / scope / non-goals
- Decision rationale + alternatives considered
- Constraints (security, performance, policy)
- Failure modes / edge cases
- Example request/response, data shape, or user flow
- Operational notes (rollout, monitoring, runbooks)
- Links to related specs/contracts
Sync rule
- After implementation/verification, promote stable context from change notes into the main context docs.
- Do not duplicate normative requirements in context docs; link back to
spec.md. - Never create or update a
docs/directory; keep everything underopenspec/.
Prompt snippet
"Keep spec.md strictly for requirements. Add/update context.md with purpose, decisions, constraints, failure modes, and at least one concrete example."
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 · 49 lines · 52 tokens per session scan A d00a9d2b551b
openspec-context-docs is a skill published in the GitHub repository Soju06/codex-lb (2,907 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 446 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
meeting-facilitate
组织多 Agent 会议全生命周期——创建会议、spawn 真实参与者、推进轮次、签到校验、结束汇总。当需要多方协作做决策、评审方案、辩论分歧、复盘项目、头脑风暴或方案评估时使用本技能。.
os-workflow
在 AI Team OS 项目里使用 CC 内置 Workflow（ultracode）时，让工作流产出回写 OS 的标准做法。当 Leader 准备调用 Workflow 工具编排子 agent 时使用。.
codexu-release
Run this skill from the repository root. Treat the release as a real public publish: verify the current remote state first, keep unrelated user changes out of release commits, and report exactly what was built, pushed, and released.
codexu-pr-review
Review codexU pull requests and decide whether they should be merged, changed, split, declined, or kept as a fork based on product positioning, roadmap, privacy, data semantics, native macOS design, architecture, scope, and verification. Use for PR review, mergeability assessment, contribution triage, and feature-fit…
meeting-participate
Participate in AI Team OS meetings with structured discussion rounds.
os-release
发布 AI Team OS 新版本的完整清单——预检、版本七处锁步、中英双语 CHANGELOG、双份 dist 构建、私有术语扫描、commit/tag、双仓推送、建 GitHub Release 条目并核对 latest 徽章、事后核对。当准备发版、补建漏掉的 Release 条目、或核对已发版本的线上状态时使用。.