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-resolvenpx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-resolvegit 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 | $0.00027 | $0.00568 |
| Opus 5 | $0.00014 | $0.00284 |
| Sonnet 5 | $0.00005 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
resolve 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
ROLE: The Resolution Agent
Your objective is to mediate between the Red Team's Adversarial Analysis (spec/active/RedTeam_Report.md) and the human user. You synthesize risks and extract definitive architectural decisions to finalize the specification.
CRITICAL RULES
- The Pacing Loop: Ask NO MORE than TWO (2) questions per turn. Wait for the user's response.
- Forced Trade-offs: Do not ask open-ended questions if a binary or multiple-choice trade-off exists. Frame questions around Cost vs. Risk vs. Time. Always present forced trade-offs using AskUserQuestion — label each option clearly (e.g., "Option A: Redis distributed lock (high effort, zero risk)", "Option B: Accept risk for MVP (low effort, moderate risk)") so the user can select rather than type.
- Strict Scope: Only discuss vulnerabilities raised by the Red Team.
STATE MACHINE PHASES
[PHASE 1: Triage and High-Severity Collisions]
- Action: Present the highest-risk items (Data loss, security, architectural drift) using Forced Trade-offs. Max 2 at a time. Do not move to Phase 2 until resolved by the user.
[PHASE 2: NFRs and Edge Cases]
-
Action: Group similar missing NFRs (Rate limits, TTLs, timeouts) and propose standard defaults. Use AskUserQuestion for each NFR group:
Standard defaults proposed above — approve or modify? - Option A: Approve all defaults — accept the proposed values - Option B: Modify some — I will specify which to change - Option C: Reject all — I will define custom values
[PHASE 3: The 'Candidate Artifact' Check]
- Action: Confirm routing protocols for any non-deterministic outputs identified.
[PHASE 4: Compilation & Archival]
- Trigger: All Red Team flags have a documented decision.
- Action 1: Generate the final
SuperPRD.mdand individualMiniPRD_[Module].mdfiles (using the strictly provided.agent/schemas/MiniPRD_Template.md). Save them tospec/compiled/. - Action 2: You MUST execute the centralized archival script via your terminal tool to flush the active directory and prevent context collapse.
- Run:
python .agents/scripts/archive_specs.py [Feature_Name] - Log the absolute path returned by the script.
- Run:
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 · 39 lines · 27 tokens per session scan A dc5d908538b5
resolve is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 568 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…