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-process-documentnpx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-process-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 | $0.00040 | $0.01351 |
| Opus 5 | $0.00020 | $0.00675 |
| Sonnet 5 | $0.00008 | $0.00270 |
| Haiku 4.5 | $0.00004 | $0.00135 |
Grade A, and why
process-document scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hyper-Process-Document
Write a process document that captures the how of this session — the problem, approach, decisions, and steps taken — so that someone reading it cold can understand and reproduce the results.
This is distinct from /hyper-handoff, which is forward-looking (context for a new agent to continue). This document is retrospective and human-readable: institutional knowledge capture.
Step 1 — Determine Output Path
Create the output directory if it does not exist:
mkdir -p spec/process
Name the file: process_<YYYYMMDD>_<slug>.md
- Use the current date for
<YYYYMMDD>(date only — no time component) - Derive
<slug>from$ARGUMENTSby lowercasing and replacing spaces/special characters with hyphens (e.g., "Dynamic Workflow Engine" →dynamic-workflow-engine) - If no
$ARGUMENTSprovided, usesessionas the slug
Disambiguate same-day documents with a version suffix. If a file with that exact name already exists (e.g. more than one process document is written on the same date), append _v2, _v3, … to the end of the filename — before the .md extension — using the next unused number. The first document of the day carries no suffix:
base="spec/process/process_$(date +%Y%m%d)_<slug>" # substitute the real <slug>
path="${base}.md"
n=2
while [ -e "$path" ]; do
path="${base}_v${n}.md"
n=$((n + 1))
done
# $path is now collision-free, e.g.
# spec/process/process_20260616_dynamic-workflow-engine.md (first of the day)
# spec/process/process_20260616_dynamic-workflow-engine_v2.md (second of the day)
Step 2 — Gather Context
Before writing, read and recall the following to reconstruct an accurate picture:
git log --oneline -20
git diff HEAD~5..HEAD --name-only
- Read
.agents/memory/activeContext.md— current sprint state and recent decisions - List
spec/active/— any in-progress PRDs or artifacts touched this session - Recall the conversation: what problems were raised, what approaches were tried, what choices were made and why
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 · 165 lines · 40 tokens per session scan A d099b45c3226
process-document is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 1,351 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…