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/tjmustard/hypergraph-coding-agent-framework/hyper-documentnpx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-documentgit clone --depth 1 https://github.com/tjmustard/Hypergraph-Coding-Agent-FrameworkWhat 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 | $0.00055 | $0.01876 |
| Opus 5 | $0.00028 | $0.00938 |
| Sonnet 5 | $0.00011 | $0.00375 |
| Haiku 4.5 | $0.00006 | $0.00188 |
Grade A, and why
hyper-document 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyper-Document
This skill updates the full documentation suite after changes to the codebase, skills, or framework structure. It reads actual implementation before writing anything — existing documentation is treated as potentially stale.
When to use this skill
- After completing a feature, bug fix, refactor, or skill change.
- When
README.md,CHANGELOG.md,docs/, or other docs are out of sync with the codebase. - When the user explicitly runs
/hyper-document.
Step 1 — Identify What Changed
Run the following to understand scope:
git log --oneline -10
git diff HEAD~1 --name-only
Identify:
- Which files were modified, added, or deleted.
- Whether the change is user-facing (affects README, CHANGELOG, docs) or internal (affects memory files, skills-info).
- Whether any skills were added, renamed, or removed.
Step 2 — Read Before Writing
CRITICAL: Do NOT trust existing documentation. Read the actual implementation.
- Read every changed file before updating any doc.
- Note discrepancies between existing docs and actual behavior.
- Never assume — verify.
Step 3 — Update Documentation by Target
Work through each target below. Skip targets that are clearly unaffected by the change.
README.md
Purpose: Entry point for new users and project overview.
Update when: Architecture changes, new features, new IDE support, install/uninstall changes, workflow changes, new slash commands, or directory structure changes.
Style rules:
- Lead with what it does, not how it works.
- Use H2 (
##) for top-level sections, H3 (###) for subsections. - Prefer tables for structured comparisons (IDE support, installed paths, commands).
- Use fenced code blocks with language tags for all commands and examples.
- Bullet lists for feature enumerations; numbered lists for sequential steps only.
- No marketing language. No "powerful", "robust", "seamless".
- Every slash command mentioned must use the
hyper-prefix (e.g./hyper-architect). - Callout blocks (
> **Note:**) for caveats, naming conventions, and non-obvious behaviors.
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 · 208 lines · 55 tokens per session scan A ef4d1c053c25
hyper-document is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,876 once invoked, about $0.0003 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…