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-troubleshootingnpx skills add tjmustard/Hypergraph-Coding-Agent-Framework --skill hyper-troubleshootinggit 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 | $0.00045 | $0.00925 |
| Opus 5 | $0.00023 | $0.00463 |
| Sonnet 5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
troubleshooting 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooting
This skill helps diagnose and recover from common failure states in the Hypergraph Coding Agent Framework. Since LLMs are probabilistic engines, they can occasionally fail even with rigid constraints.
When to use this skill
- When the user reports an agent is writing code for rejected features.
- When the
/hyper-auditagent fails or/hyper-redteamhallucinates the Blast Radius. - When the Red Team report suggests new product features instead of vulnerabilities.
- When
architecture.ymlthrows a ParserError or gets corrupted. - When the Architect Agent asks the same questions repeatedly and won't generate a PRD.
- When the user explicitly runs
/hyper-troubleshooting.
How to use it
Step 1: Identify the Symptom
Use AskUserQuestion to identify the symptom:
What symptom are you seeing?
- Option A: Context Bloat / Hallucination — Builder is writing code for rejected features
- Option B: Hypergraph Desync — /hyper-audit or /hyper-redteam fails or has wrong blast radius
- Option C: YAML Corruption or Infinite Loop Interview — architecture.yml parse error, or Architect repeatedly asks the same questions
- Option D: Red Team Scope Creep — Red Team report suggests product features instead of vulnerabilities
If the user selects Option C, ask a brief follow-up to confirm whether it is the YAML corruption or the infinite loop interview before applying the fix.
Step 2: Provide Diagnosis and Fix
Issue 1: Context Bloat & Hallucination
Cause: The agent's context window is polluted with old data. Active specs were not archived. Fix:
- Halt the Builder Agent.
- Ensure
.agentignorecontainsspec/archive/. - Run
python .agents/scripts/archive_specs.py cleanup. - Open a completely new agent chat and restart the Builder prompt pointing strictly to the compiled MiniPRD.
Issue 2: Hypergraph Desynchronization
Cause: The Builder forgot or failed to execute hypergraph_updater.py, so architecture.yml is unaware of codebase changes.
Fix:
- Look at the modified files and identify their
node_ids inarchitecture.yml. - Manually execute:
python .agents/scripts/hypergraph_updater.py spec/compiled/architecture.yml [node_id_1] [node_id_2] - Re-run
/hyper-auditto perform the semantic update.
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 · 84 lines · 45 tokens per session scan A c8ddf9536da3
troubleshooting is a skill published in the GitHub repository tjmustard/Hypergraph-Coding-Agent-Framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 925 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.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.