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/waelmas/codeplow/kb-graphnpx skills add waelmas/codeplow --skill kb-graphgit clone --depth 1 https://github.com/waelmas/codeplowWhat 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 | $0.00088 | $0.01430 |
| Opus 5 | $0.00044 | $0.00715 |
| Sonnet 5 | $0.00018 | $0.00286 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
kb-graph scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kb-graph - Open Vault in Graph View
Open Obsidian at the project's vault and switch to the graph view. Pure convenience - makes the knowledge base visible as an explorable network rather than a file tree.
Step 0: Preflight - Obsidian available and running?
Follow the Preflight Check in the obsidian-kb awareness skill (${CLAUDE_PLUGIN_ROOT}/skills/obsidian-kb/SKILL.md). In short:
command -v obsidian- if missing, check if the app is installed; if neither, show cross-platform install instructions (brew install --cask obsidian/flatpak install flathub md.obsidian.Obsidian/winget install Obsidian.Obsidian, or https://obsidian.md/download) and stop.timeout 3 obsidian vaults- if it fails, launch Obsidian (open -a Obsidianon macOS, equivalent for Linux/Windows), wait 2-3 seconds, retry.- Only proceed once
obsidian vaultssucceeds.
Step 1: Resolve the Project Vault (strict)
Follow the Vault Resolution Algorithm in ${CLAUDE_PLUGIN_ROOT}/skills/obsidian-kb/SKILL.md. Strict priority order:
- User argument (vault name) → fuzzy-match once, confirm.
- Path overlap - exactly one vault whose path is inside
$PWDor vice versa. - Frontmatter
project_path- a root note's YAML matches$PWDexactly. - Strong name match - word-boundary substring match, exactly one candidate.
- STOP and ask - if tiers 1–4 fail, list vaults and ask. Do NOT default. Do NOT fall back to the active Obsidian vault.
After resolution, print the confirmation line:
"Opening vault
<Vault Name>at<path>(matched via<tier>). Say 'wrong vault' if I should pick a different one."
Critical: the obsidian URI you open in Step 2 MUST use the resolved vault name - never let Obsidian decide which vault to open.
If no vault exists for this project (Tier 5 → user chose "create a new one"): offer to chain through /kb-init first, then return to this skill:
"No knowledge base vault found for this project. I can run /kb-init to create and populate one with codebase documentation, then come back to open the graph view. Takes 3-6 minutes. Proceed? [Y/n]"
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 · 112 lines · 88 tokens per session scan A 3e0e035e9beb
kb-graph is a skill published in the GitHub repository waelmas/codeplow (8 stars, last pushed 4mo ago), licensed MIT. It adds 88 tokens to every session and 1,430 once invoked, about $0.0004 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…