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/context4ai/workflow/make-kbnpx skills add context4ai/workflow --skill make-kbgit clone --depth 1 https://github.com/context4ai/workflowWhat 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 | $0.00043 | $0.04211 |
| Opus 5 | $0.00022 | $0.02106 |
| Sonnet 5 | $0.00009 | $0.00842 |
| Haiku 4.5 | $0.00004 | $0.00421 |
Grade A, and why
make-kb 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 — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/make-kb - Knowledge Base Generation (Source-Traced Graph)
Extract structured knowledge graphs from existing materials — documents, code, or both — with <!-- source: path --> traceability on every Node.
Difference from /make-prd and /make-plan:
/make-prddesigns a PRD forward from requirement descriptions (new features, RFCs)/make-plandesigns a Plan forward from a PRD/make-kbworks backward from existing artifacts — it reads what already exists and organizes it into a structured graph. The output represents current state, not planned changes
Applicable to both technical and non-technical projects:
- Technical: codebase architecture, API documentation, system design docs
- Non-technical: business processes, organizational knowledge, policy documents, research notes, operational runbooks
TL;DR -- Hard Rules
- Input: File/directory paths + version number (required)
- Output:
<design-dir>/<version>/prd.md(knowledge graph), optionallyplan.md(code graph when code is provided) - Every Node must have
<!-- source: path -->or<!-- source: path#LN -->pointing to the originating file - All Nodes default to
[existing]— this is a snapshot, not a change plan - Do not fabricate source paths — every
<!-- source: -->must point to a file the Agent has actually read - Code layer is optional — docs-only produces prd.md; adding code produces plan.md with
correspondsedges linking the two layers - Adapt the graph depth to the material — a small doc may only need domain + a few stories; a large project may need the full three-layer hierarchy
Design Workspace (design-dir)
The default workspace for design documents is design/. When the Agent starts, check:
design/directory exists -> usedesign/as<design-dir>design/does not exist -> pause and ask the user for the design workspace path, explaining the accepted directory structure:<design-dir>/<version>/(prd|plan).md Examples: design/v1.0.1/prd.md, design/v0.5.0/plan.md
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 First seen · 414 lines · 43 tokens per session scan A 58d6f6197fc2
make-kb is a skill published in the GitHub repository context4ai/workflow (4 stars, last pushed 4mo ago), licensed MIT. It adds 43 tokens to every session and 4,211 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…