Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/conorbronsdon/agent-context-osnpx agentmods add skills/conorbronsdon/agent-context-os/context-startWrote 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/context-start)<a href="https://agentmods.dev/skills/conorbronsdon/agent-context-os/context-start"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-context-os/context-start/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/context-start"><img src="https://agentmods.dev/badge/skills/conorbronsdon/agent-context-os/context-start.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 | $0.00042 | $0.01279 |
| Opus 5.5 | $0.00017 | $0.00512 |
| Sonnet 5.5 | $0.00008 | $0.00256 |
| Haiku 4.5 | $0.00004 | $0.00128 |
Grade A, and why
context-start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a workspace session
Execution roots (required)
When the host executes commands inside Bash, replace the bash executable
shown below with "$BASH" to reuse that shell. This avoids selecting a different
Bash from PATH, such as the Windows WSL launcher inside a Git Bash session.
In a terminal outside Bash, select the installed Bash explicitly.
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 routing, state, session, task, and local
Context OS paths beneath ContextRoot. In split mode, 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.
Resume from durable repository state instead of reconstructing context from chat history.
Procedure
-
Run exactly one start form:
split: bash <KernelRoot>/scripts/contextos.sh --context-root <ContextRoot> --working-root <WorkingRoot> start colocated: bash scripts/contextos.sh startTreat its JSON as the deterministic inventory of configured paths, freshness, latest session, and role-qualified Git evidence. In colocated mode, the compatibility
git_headdescribes the documentedGitEvidenceScope, which may enclose ContextRoot. If the kernel is unavailable, stop and recommend the matching doctor form:
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.
- 11d ago Changed · +5 lines d1f7c0001d9e
- 25d ago Changed · +2 lines d44a03c7f60c
- 1mo ago Changed · +9 lines 594e87e1464a
- 1mo ago Changed · +34 lines e2897e79f7e4
- 1mo ago First seen · 58 lines · 42 tokens per session scan A 364006b89f2d
context-start is a skill published in the GitHub repository conorbronsdon/agent-context-os (29 stars, last pushed 5d ago), licensed MIT. It adds 42 tokens to every session and 1,279 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
next-cache-components
Next.js 16 Cache Components guidance. Use when refactoring React Server Components for performance, debugging Partial Prerendering (PPR) issues, or applying the use cache directive, cacheLife, cacheTag, updateTag, and revalidateTag. Also use when deciding whether data should be static, cached, or dynamic, or when…
agents-sdk
Build AI agents on Cloudflare Workers using the Agents SDK or build Model Context Protocol (MCP) servers. Load when creating stateful agents, durable workflows, MCP servers, checking MCP schema/error responses, or reviewing MCP code quality. Covers Agent class, state management, callable RPC, Workflows integration…
github-actions
Master GitHub Actions CI/CD workflows with production-grade security and performance patterns. Use ONLY when explicitly setting up CI/CD pipelines specifically via GitHub Actions, setting up matrix strategies, caching dependencies, managing artifacts, or implementing reusable workflows. For deployment requests, use…
workers-best-practices
(APPLICATION CODE ONLY) Reviews and authors Cloudflare Workers code against production best practices. Use ONLY when writing or reviewing Worker code, configuring wrangler.jsonc, or checking for anti-patterns. Do NOT use for general Cloudflare product discovery (use cloudflare instead) or CLI management (use wrangler…
github-commander
Structured workflows for GitHub issues, PRs, milestones, and code audits with validation gates and HITL checkpoints. Use when assigned a GitHub issue, reviewing a PR, sprinting through a milestone, updating dependencies, or running code audits. Also use when asked to "triage an issue", "review a PR", or "update deps".…
python
Master modern Python development with production-grade tooling and idioms. Use when writing Python code, configuring project structure, managing dependencies with uv, linting with ruff, adding type hints, writing pytest tests, or building FastAPI/Django/Flask applications. Triggers on "Python", "FastAPI", "Django"…