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-sopnpx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-sopgit 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 | $0.00038 | $0.00865 |
| Opus 5 | $0.00019 | $0.00432 |
| Sonnet 5 | $0.00008 | $0.00173 |
| Haiku 4.5 | $0.00004 | $0.00086 |
Grade A, and why
sop 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hyper-sop — Master Standard Operating Procedure Guide
This skill guides the user through the Master Standard Operating Procedure (SOP) of the Hypergraph Coding Agent Framework.
The framework relies on a strict sequential model — Spec-First, Deterministic Memory, and Automated Auditing — to prevent context collapse and hallucinated requirements.
Step 1: Introduction
Briefly introduce the Hypergraph framework's core paradigm:
- The workflow is strictly sequential.
- Specialized agents handle distinct phases (Architect, Red Team, Resolution, Auditor).
- Deterministic Python scripts manage state so LLMs never traverse the graph probabilistically.
- New context windows (new conversations) prevent cross-contamination between adversarial agents.
Step 2: Determine User State
Use AskUserQuestion to determine the user's current state:
Which phase of the framework are you in?
- Option A: Phase -1: Legacy Onboarding — Integrating the framework into an existing project
- Option B: Phase 0: Initialization — Starting a brand new greenfield project
- Option C: Phase 1: Specification — Planning and designing a new feature
- Option D: Phase 2: Execution — Writing code against a compiled MiniPRD
Step 3: Provide Phase-Specific Guidance
Wait for the user's response, then provide the exact steps:
Phase -1 (Legacy Onboarding):
- Run
/hyper-discover— scans the codebase and populatesspec/compiled/architecture.yml. - Review the generated YAML for accuracy.
- Run
/hyper-baseline— generates the initialSuperPRD.md. - Once verified, proceed to Phase 1.
Phase 0 (System Initialization):
- Ensure the template is cloned with
.agents/andspec/directories intact. - Install the dependency:
pip install pyyaml - Give execution permissions:
chmod +x .agents/scripts/*.py - The workspace is ready. Proceed to Phase 1.
Phase 1 (Specification):
- Run
/hyper-architect— begins the requirements extraction interview (createsDraft_PRD.mdinspec/active/). - Start a new conversation and run
/hyper-redteam— adversarial analysis (createsRedTeam_Report.mdinspec/active/). - Start a new conversation and run
/hyper-resolve— resolves trade-offs and compilesSuperPRD.mdandMiniPRDfiles intospec/compiled/. - The resolve agent will automatically run
python .agents/scripts/archive_specs.py [Feature_Name]to flush active drafts.
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 · 76 lines · 38 tokens per session scan A 6949cb488380
sop is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 865 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…