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 conorbronsdon/agent-context-os --skill contextos-workspacegit clone --depth 1 https://github.com/conorbronsdon/agent-context-osWrote 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/conorbronsdon/agent-context-os/contextos-workspace)<a href="https://agentmods.dev/skills/conorbronsdon/agent-context-os/contextos-workspace"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-context-os/contextos-workspace/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/conorbronsdon/agent-context-os/contextos-workspace"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-context-os/contextos-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.00365 |
| Opus 5 | $0.00019 | $0.00182 |
| Sonnet 5 | $0.00008 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
contextos-workspace 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
Context OS workspace companion
- Identify the user's intended Context OS workspace. Ask for its path if it is not explicit or unambiguous. Never use the plugin installation/cache as a workspace, and never create a workspace or import context implicitly.
- Verify the selected root contains
AGENTS.md,ROUTING.md,scripts/contextos.sh, and.agents/skills/. If not, stop and explain the repository-native setup in the bundleddocs/codex-onboarding.md(relative to the plugin root, two directories above this file). - Read that workspace's
AGENTS.md,ROUTING.md, anddocs/safety-contract.mdcompletely. Use that workspace as the working directory. Do not mix installed-plugin code with another workspace's state. - For the operation the user requested, read its canonical
.agents/skills/context-setup/SKILL.md,context-start/SKILL.md,context-update/SKILL.md, orcontext-end/SKILL.mdin the selected workspace. Follow that file; do not substitute a plugin-local copy or infer an operation that would expand the request. - Start is read-only. Setup, update and end require a displayed proposal and explicit approval of its exact digest before apply. Never write lifecycle state directly, install hooks, or commit/push implicitly. Report receipts and verification limits. Plugin installation grants no extra authority.
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 · 28 lines · 38 tokens per session scan A a28e784c8dbb
contextos-workspace is a skill published in the GitHub repository conorbronsdon/agent-context-os (24 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 365 once invoked, about $0.0002 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 2026-09-08.
Other skills, from other repositories
layered-context
L0/L1/L2 three-layer context loading protocol — reduces token consumption during /resume boot.
semantic-search
Zero-dependency TF-IDF search across MUSE memory, roles, and skills. Use when user wants to find information across their project context.
handoff
Create, validate, list, and load local Portable Handoff capsules for context transfer, continuing work in a new chat, compacting current work, or loading prior work. Use whenever the user asks for a handoff, context transfer, continuation briefing, or portable work-state summary.
pace-knowledge
Use for PACEflow knowledge/thoughts notes, finding-to-knowledge extraction, correction knowledge links, and Obsidian frontmatter/L0-L2 note structure.
memory-audit
Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped…
close-session
An end-of-session workflow that reviews new lessons, asks before promoting repeated patterns, refreshes memory files, and writes a handoff.