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 wrg32786/aigent-os --skill solution-huntgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/solution-hunt)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/solution-hunt"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/solution-hunt/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/wrg32786/aigent-os/solution-hunt"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/solution-hunt.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 | $0.00000 | $0.00762 |
| Opus 5 | $0.00000 | $0.00381 |
| Sonnet 5 | $0.00000 | $0.00152 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
solution-hunt 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 7d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/solution-hunt — Creative workaround engine
When blocked, systematically search for legitimate alternate routes before declaring inability.
Trigger
/solution-hunt <blocker description> or /solution-hunt (asks for blocker)
Flow
1. Define the blocker
From argument or ask: "What's blocking you?" Get a concrete description of what can't be done and why.
2. Search local memory
Grep the vault for related concepts, prior solutions, similar blockers:
Grep pattern: {blocker keywords} in $AIGENT_VAULT/
3. Search local skills
Read $AIGENT_VAULT/memory/SKILL_LEDGER.md. Prefix-match against taxonomy paths. Check memory/SKILL_CHAINS.md for prior chains that solved similar problems.
4. Search GitHub
mcp__github__search_repositories: "{blocker} workaround" OR "{blocker} alternative"
mcp__github__search_code: "{specific error or API}" language:typescript OR language:python
5. Search docs and web
mcp__tavily__tavily_search: "{blocker} workaround" OR "{blocker} alternative solution"
mcp__tavily__tavily_extract: {relevant doc URLs found}
6. Identify 3 routes
| Route | Description |
|---|---|
| Direct fix | Solve the root cause — fix the bug, update the dep, change the config |
| Workaround | Legitimate alternate path — different API, different tool, decompose the task |
| Replace component | Swap the blocking tool/dependency entirely |
7. Rank by tradeoffs
| Factor | Weight |
|---|---|
| Speed to implement | High |
| Risk of side effects | High |
| Maintainability | Medium |
| Cost (tokens, API calls, money) | Medium |
8. Present top 3
For each route, show:
- Description (1-2 sentences)
- Tradeoffs (speed/risk/maintenance)
- Confidence (high/medium/low)
- Implementation steps (3-5 bullets)
9. Execute chosen path
On user selection, implement the chosen route. If it requires a new skill, route through /skill-hunt.
10. Capture learning
- If the solution involved a new pattern: log to
memory/SKILL_CHAINS.md - If it exposed a gap: log to
memory/SKILL_GAPS.md - If it fixed a recurring issue: log to
memory/FAILURE_MODES.mdvia/learn-from-failure
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.
- 7d ago First seen · 87 lines · 0 tokens per session scan A 77f48d0f05d2
solution-hunt is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 762 tokens. 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 2026-09-03.
Other skills, from other repositories
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
triage-issue
Analyze a GitHub issue, verify claims against the codebase, and close invalid issues with a technical response.
hive.error-recovery
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
skill-repair
Diagnose and fix failing or degraded skills automatically - systemic-first triage, per-category playbooks, and a verification plan.
self-improve
Improve the agent itself, or audit its recent performance - better skills, prompts, workflows, and config, plus a quality/reliability/memory-hygiene review of what it did and what failed.
systematic-debugging
Systematic approach to diagnosing and fixing errors.