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 skills add WingedGuardian/GENesis-AGI --skill obstacle-resolutiongit clone --depth 1 https://github.com/WingedGuardian/GENesis-AGIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/wingedguardian/genesis-agi/obstacle-resolution)<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/obstacle-resolution"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/obstacle-resolution/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wingedguardian/genesis-agi/obstacle-resolution"><img src="https://agentmods.dev/badge/skills/wingedguardian/genesis-agi/obstacle-resolution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00037 | $0.00630 |
| Opus 5 | $0.00018 | $0.00315 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
obstacle-resolution 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 9d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Obstacle Resolution
Purpose
When Genesis encounters a blocker — a failed API call, an unavailable service, a missing capability — systematically resolve it using the fallback chain framework.
When to Use
- A routing chain is exhausted (all providers failed).
- A required service is unreachable.
- A task cannot proceed due to a missing dependency or capability.
- Automatic retries have been exhausted.
Workflow
- Classify the obstacle — What type? (provider failure, data missing, capability gap, external dependency, permission issue)
- Check fallback chain — Load the relevant fallback chain from
fallback_chains.py. Walk the chain in order. - Attempt each fallback — Try each alternative. Log attempts and results.
- Escalate if needed — If all fallbacks exhausted:
- For non-urgent: queue for user review, continue with degraded capability.
- For urgent: alert user immediately via outreach.
- Record resolution — Store the successful resolution path as an observation. If a new fallback was discovered, propose a procedure update.
Output Format
obstacle: <one-line description>
date: <YYYY-MM-DD>
type: provider_failure | data_missing | capability_gap | external_dep | permission
chain_attempted:
- step: <fallback step>
result: success | failure
detail: <what happened>
resolution: resolved | degraded | escalated
resolution_detail: <how it was resolved>
Examples
Example: Embedding provider chain exhausted
Trigger: memory_store fails with EmbeddingUnavailableError — Ollama timeout, DeepInfra 429, DashScope connection refused.
Expected output:
obstacle: All embedding providers exhausted during memory store
date: 2026-03-20
type: provider_failure
chain_attempted:
- step: Ollama (local)
result: failure
detail: ReadTimeout after 60s — model not loaded
- step: DeepInfra (cloud)
result: failure
detail: HTTP 429 rate limit (RPM exceeded)
- step: DashScope (cloud)
result: failure
detail: ConnectionRefusedError — service unreachable
resolution: degraded
resolution_detail: Memory stored FTS5-only (no vector). Queued in
pending_embeddings for background recovery. Circuit breaker tripped
on DashScope (120s backoff).
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.
- 9d ago First seen · 85 lines · 37 tokens per session scan A d6b7ffbc2725
obstacle-resolution is a skill published in the GitHub repository WingedGuardian/GENesis-AGI (96 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 630 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 2026-08-30.
Other skills, from other repositories
distributed-tracing
Implement distributed tracing with Jaeger and Tempo for request flow visibility across microservices.
langfuse
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production.
incident-responder
Expert SRE incident responder specializing in rapid problem resolution, modern observability, and comprehensive incident management.
arch-debt
Identify architectural anti-patterns — coupling, circular dependencies, God objects — and propose concrete migration paths.
chaos-fault-injection
Deliberately inject faults — dropped connections, corrupted writes, latency, malformed responses, resource exhaustion — and assert the system's expected recovery (escalation, hardstop, rollback).
self-heal
Autonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation.