A command for loading project-specific instructions from Context Forge, a system that builds a working context prompt from project information. It can load the whole project or a selected phase or slice.

Building or refreshing Context Forge context from a project root, optionally for a particular phase or slice, and then following the generated instructions.

It gives the coding agent the project context needed before work begins. If the context build fails or says to stop, the process prevents work from starting with incomplete instructions.

cf-build — Skill by ecorkran

Install

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.

agentmods

npx agentmods add skills/ecorkran/context-forge/cf-build

Any agent

npx skills add ecorkran/context-forge --skill cf-build

Clone the repo

git clone --depth 1 https://github.com/ecorkran/context-forge

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 190 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00036	$0.00190
Opus 5	$0.00018	$0.00095
Sonnet 5	$0.00007	$0.00038
Haiku 4.5	$0.00004	$0.00019

Measured 2d ago against content hash 7a747336bb21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cf-build 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.

packages/cli/commands/codex/cf-build/SKILL.md · 18 lines

What it actually says

Context Forge Build

Run cf build --json from the project root. If the user supplied a phase or slice, pass it with --phase <phase> or --slice <slice>.
If the command fails, show its error output and stop.
Use the returned prompt as your working context.
Confirm receipt with exactly one line: Context loaded: {project} | {phase} | {slice} — take the three values from the command's output.
Follow the instruction prompt contained in the generated context.
If the instruction prompt contains a STOP condition, STOP — do not begin work; request the required input instead.

Changes

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 · 18 lines · 36 tokens per session scan A 7a747336bb21

Subscribe to this mod's changes

cf-build is a skill published in the GitHub repository ecorkran/context-forge (5 stars, last pushed 21d ago), licensed MIT. It adds 36 tokens to every session and 190 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 2026-08-31.

Data and AI claude-code cli mcp mcp-server

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens