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/conorbronsdon/agent-context-os/context-setupnpx skills add conorbronsdon/agent-context-os --skill context-setupgit clone --depth 1 https://github.com/conorbronsdon/agent-context-osWhat 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 | $0.00044 | $0.01118 |
| Opus 5 | $0.00022 | $0.00559 |
| Sonnet 5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
context-setup 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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up workspace context
Execution roots (required)
Use the exact roots supplied by the host attachment: KernelRoot is the trusted
Context OS product containing scripts/contextos.sh; ContextRoot owns tracked
identity and lifecycle state; and WorkingRoot is the ordinary application.
For an external attachment, require all three exact absolute paths and run:
bash <KernelRoot>/scripts/contextos.sh --context-root <ContextRoot> --working-root <WorkingRoot> <command>
Do not search upward or infer a root from cwd or the skill installation. The
kernel must validate the ignored local binding before strict lifecycle work. A
missing, moved, stale, linked, nested, or mismatched binding stops the workflow;
use the explicit project rebind proposal after a legitimate move. ContextRoot
owns all lifecycle writes. WorkingRoot is read-only evidence. The colocated
bash scripts/contextos.sh <command> compatibility form remains valid.
Throughout this procedure, resolve every context path beneath ContextRoot. In
split mode, spell local paths as absolute <ContextRoot>/... paths and invoke
every lifecycle command through the absolute KernelRoot wrapper with both exact
role options. In colocated mode, run the relative compatibility commands from
the colocated root, where ContextRoot and WorkingRoot are the same directory.
Build useful context without silently overwriting user data.
Guardrails
- Ask questions one at a time and inspect existing files before proposing changes.
- Preserve the user's wording; do not embellish credentials, goals, or biography.
- Require approval before replacing populated files, broad writes, commits, or pushes.
- Never request or store credentials or ingest a raw account export into tracked context.
Procedure
1. Confirm storage and audience
Explain that tracked identity, project, state, session, and imported context is visible to repository collaborators and configured agents. Deleting it later does not erase git history. Recommend local-only or private storage by default; a public remote requires deliberately sanitized content. Stop before collecting personal information unless the user explicitly confirms the audience.
What ships with it
1 file 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.
- yesterday Changed · +23 lines bcbf5cf85e7a
- 3d ago First seen · 87 lines · 44 tokens per session scan A 45ad41bc67e6
context-setup is a skill published in the GitHub repository conorbronsdon/agent-context-os (17 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 1,118 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 2026-08-30.
Other skills, from other repositories
alive:world
The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.
alive:bundle
Create, share, and graduate bundles — the unit of focused work within a walnut. Manages the full bundle lifecycle from creation through sharing to graduation.
alive:settings
The human wants to adjust how the system behaves — not what it contains, but how it feels. Voice, rhythm, preferences, walnut-level config, full permissions toggleable, named squirrel config, action logging toggle. The system adapting to them. Routes to preferences.yaml or walnut config.yaml depending on scope. For…
alive-cleanup
System maintenance -- stale tasks, orphan folders, unsaved sessions, world health check.
alive-morning
Morning briefing -- read all walnut states, surface priorities, inbox count, stale walnuts, people nudges.
cco-budget
Configure token budget limits, auto-compact settings, and view current budget status (model-aware — Opus 4.8 default, full 1M context at standard price).