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/drn/dots/knowledgenpx skills add drn/dots --skill knowledgegit clone --depth 1 https://github.com/drn/dotsWhat 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 | $0.00026 | $0.00861 |
| Opus 5 | $0.00013 | $0.00430 |
| Sonnet 5 | $0.00005 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
knowledge 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base
Manage a structured knowledge base at context/knowledge/ for capturing durable facts, entities, and patterns across sessions.
Arguments
$ARGUMENTS- Subcommand:init,add <topic>,update <topic>, or omit for status
Context
- Knowledge index: !
cat context/knowledge/index.md 2>/dev/null | head -50 - Knowledge files: !
find context/knowledge -maxdepth 1 -name "*.md" 2>/dev/null | head -20 - Project root: !
git rev-parse --show-toplevel 2>/dev/null | head -1 - CLAUDE.md exists: !
find . -maxdepth 1 \( -name CLAUDE.md -o -name AGENTS.md \) 2>/dev/null | head -2
Instructions
Subcommand: init
Create the knowledge base directory and seed it with an index file.
- Create
context/knowledge/directory - Write
context/knowledge/index.mdwith this template:
# Knowledge Index
Structured knowledge for future knowledge graph ingestion. Each file covers a topic/domain.
| File | Topic | Key Entities | Last Updated |
|------|-------|-------------|-------------|
## Coverage Map
Which context files are captured in knowledge:
| Context File | Knowledge File(s) | Coverage |
|-------------|-------------------|----------|
- If the project has a
.gitignore, verifycontext/knowledge/is not ignored - Report the path created and suggest initial topics based on what is visible in the repo (CLAUDE.md, AGENTS.md, README, directory structure)
Subcommand: add
Create a new topic file and register it in the index.
- Read the existing index to avoid duplicates
- Ask what entities and facts to capture if not obvious from conversation context
- Create
context/knowledge/<topic>.mdwith a heading and structured content - Update
context/knowledge/index.md— add a row to the index table with the file name, topic description, key entities, and today's date - Report what was added
Subcommand: update
Update an existing topic file with new knowledge.
- Read
context/knowledge/index.mdto find the topic file - Read the topic file
- Propose additions or corrections as diffs
- Apply after user approval
- Update the Last Updated date in
context/knowledge/index.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.
- 2d ago First seen · 117 lines · 26 tokens per session scan A e8e66b762122
knowledge is a skill published in the GitHub repository drn/dots (23 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 861 once invoked, about $0.0001 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 2026-08-30.
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…