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/dixus/claudeframework/docnpx skills add dixus/claudeframework --skill docgit clone --depth 1 https://github.com/dixus/claudeframeworkWhat 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 | $0.00029 | $0.00518 |
| Opus 5 | $0.00015 | $0.00259 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
doc 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.
What it actually says
Regenerate the framework documentation in .claude/docs/ to reflect the current state of skills, context, and processed references.
Steps:
- Read all skill definitions in
.claude/skills/— everySKILL.mdfile - Read all context files in
.claude/context/ - Read
.claude/references/index.mdfor the processed references changelog - Read the existing docs in
.claude/docs/so you can update rather than overwrite content that is still accurate
Update each of the following files. Preserve the "Generated and maintained by /doc" header and update the "Last updated" date:
.claude/docs/README.md
- Framework overview and purpose
- Quick start workflow (skill sequence)
- Skills overview table (name, one-line purpose)
- Directory layout
.claude/docs/workflow.md
- The pipeline diagram (with all current skills)
- Rationale for each step (why it exists, what it prevents)
- Session patterns (fresh session rules, resuming, parallel sessions)
- Context hygiene rules table
- CLAUDE.md maintenance guidelines
- Knowledge base loop description
.claude/docs/skills-reference.md
- One section per skill
- For each skill: purpose, when to use, inputs, outputs, what it does (numbered), usage examples
- Keep in sync with actual SKILL.md content — if a skill was updated, update its docs section too
.claude/docs/knowledge-base.md
- Table of context files with last-updated dates
- Processed references log (one entry per processed reference, with date and key insights summary)
- Pending references section (anything in references/ not yet processed)
- Suggested references to collect (carry forward existing suggestions, add new ones if context suggests gaps)
Rules:
- Do not invent content — only document what actually exists in skills and context files
- If a skill was changed since the last doc run, update its section to match
- If a new context file was added, add it to the knowledge-base.md table
- Write for a developer reading this for the first time — explain the why, not just the what
- Keep each doc file focused — do not merge them
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 · 48 lines · 29 tokens per session scan A 0c9a43894e2d
doc is a skill published in the GitHub repository dixus/claudeframework (10 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 518 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 2026-08-31.
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…