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 build-with-dhiraj/ai-workflow-framework-portability-kit --skill context-kernelgit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/context-kernel)<a href="https://agentmods.dev/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/context-kernel"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/context-kernel/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/build-with-dhiraj/ai-workflow-framework-portability-kit/context-kernel"><img src="https://agentmods.dev/badge/skills/build-with-dhiraj/ai-workflow-framework-portability-kit/context-kernel.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 | $0.00031 | $0.02070 |
| Opus 5.5 | $0.00012 | $0.00828 |
| Sonnet 5.5 | $0.00006 | $0.00414 |
| Haiku 4.5 | $0.00003 | $0.00207 |
Grade A, and why
context-kernel 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 25d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Kernel Skill
You are now responsible for maintaining a project context kernel that survives chat forks. The kernel is a single Markdown file at <workspace>/.kernel/KERNEL.md where <workspace> is the current working directory (the project root). An append-only daily log at <workspace>/.kernel/log/YYYY-MM-DD.md is the safety net.
Purpose
In a long-running multi-session project, the user may start a new Claude Code chat (a "fork") at any time. Without the kernel, every fork is blind — they have to re-explain context. With the kernel, the orchestrator reads it as the first action on session start, briefs the user in 4–6 lines, and continues from where the prior chat left off.
After substantive turns, the kernel is updated so it never goes stale. The user reviews kernel changes via a per-response "Kernel Updates" block and corrects them at the top of their next prompt.
Path discovery
- Workspace root = the current working directory (
pwd). - Kernel file =
<workspace>/.kernel/KERNEL.md. - Log directory =
<workspace>/.kernel/log/. - Daily log file =
<workspace>/.kernel/log/<YYYY-MM-DD>.md(use system date in local timezone).
If .kernel/KERNEL.md does not exist in the workspace, this skill does NOT apply — that workspace has not been bootstrapped with a kernel. Do not auto-create one without the user's request.
Kernel schema
The kernel uses this fixed structure. Section headings are required; their order is required; their presence is validated on every read.
# Project Kernel — <project name>
Last-Updated: <ISO8601 timestamp>
Kernel-Version: 1
## North Star
<1 paragraph: what we're building, for whom, why narrow>
## Locked Decisions
- [YYYY-MM-DD] <decision> — rationale: <1 line>
- ...
## Open Questions
- <question> — blocking: <what work it blocks>
- ...
## Active Artifacts
- <type>: `<absolute path>` — current thesis (3–5 lines), last touched: <YYYY-MM-DD>
- ...
## Threats & Landmines
- <adjacent competitor, dead-end already explored, thing not to relitigate>
- ...
## Pending Hand-offs
- <what the next chat / fork should pick up first, with enough detail to act>
- ...
## Fork Checkpoint
<optional — present only when user has explicitly forked here>
- Created: <YYYY-MM-DD HH:MM>
- From-context: <what was just done in the chat that produced this checkpoint>
- Resume instructions: <explicit next 1–3 actions>
## Historical Context (compacted)
<consolidate-memory output; trimmed periodically by the Kernel Steward>
## Resume Protocol
If you are reading this at session start: brief the user with the North Star (1 line), the most recent Locked Decision, the top Open Question, the Pending Hand-off, and the Fork Checkpoint (if present). End with: "Continue from hand-off, or pivot?"
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.
- 25d ago First seen · 182 lines · 31 tokens per session scan A 389570c7ff5a
context-kernel is a skill published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (5 stars, last pushed 12d ago), licensed MIT. It adds 31 tokens to every session and 2,070 once invoked, about $0.0001 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 2026-09-21.
Other skills, from other repositories
agents-md-improver
Audit and improve project-rules files (AGENTS.md, CLAUDE.md, .agents/instructions, local overrides) so the agent keeps accurate project context. Use when the user asks to check, audit, review, update, improve, or fix their AGENTS.md or CLAUDE.md, mentions "project rules maintenance" or "agent context optimization", or…
agents-md-revise
Capture learnings from the current session into the project-rules file (AGENTS.md, CLAUDE.md, or local override) so future sessions benefit. Use when the user says "revise the rules", "update AGENTS.md / CLAUDE.md with what we just learned", "save this to project memory", "remember this for next time", or at the end…
hf-cloud-serving-image-selection
Select and verify the current region-specific serving container URI for a SageMaker model deployment. Use after the deployment pathway is chosen and before endpoint code; never infer an image URI from memory.
pith-wiki
Wiki mode — persistent knowledge base maintenance. Active during /pith wiki mode. Defines page formats, ingest workflow, query workflow, and lint checks.
hf-mem
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub.
pith-setup
Pith onboarding conversation. Runs on first session in a new project. Introduces Pith, offers wiki setup, guides through initialization. Injected by session-start.js when no prior setup detected.