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 Tenstu/Pass-LLM-with-LLM --skill solve-analyzegit clone --depth 1 https://github.com/Tenstu/Pass-LLM-with-LLMWrote 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/tenstu/pass-llm-with-llm/solve-analyze)<a href="https://agentmods.dev/skills/tenstu/pass-llm-with-llm/solve-analyze"><img src="https://agentmods.dev/badge/skills/tenstu/pass-llm-with-llm/solve-analyze/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/tenstu/pass-llm-with-llm/solve-analyze"><img src="https://agentmods.dev/badge/skills/tenstu/pass-llm-with-llm/solve-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00160 | $0.05017 |
| Opus 5 | $0.00080 | $0.02508 |
| Sonnet 5 | $0.00032 | $0.01003 |
| Haiku 4.5 | $0.00016 | $0.00502 |
Grade A, and why
solve-analyze 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 10d 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 — 455 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Solve Analyze Skill
Structured diagnosis layer that compares a user's solve() against a standard solution generated by the solve-skeleton pipeline. Produces a side-by-side diff report, identifies root cause tags, and triggers feedback loops into mistake_log, user_profile, and exam-memory MCP. This skill does not teach and does not build skeletons -- it diagnoses "what you wrote vs what you should have written."
1. Overview
Pipeline Position
solve-skeleton (template)
-> user fills logic
-> ** solve-analyze (diagnosis) ** <-- this skill
-> algo-annotation (# [防错] markers)
-> mistake_log (error record)
-> user_profile (weakness tracking)
-> choice-q-create (targeted question generation)
Purpose
When a user completes a solve() function and wants to know what went wrong, this skill:
- Performs a quick triage to determine report depth (full diagnosis vs lightweight style check).
- Statically analyzes the user's code for logic errors, anti-patterns, and suspicious lines.
- Generates a reference solution via the solve-skeleton pipeline.
- Produces a structured comparison report highlighting every meaningful difference.
- Extracts root cause tags and feeds them back into the harness feedback loops.
The output is actionable: each identified issue maps to a specific root cause tag, a suggested fix, and an automatic (or user-confirmed) write to the error tracking system.
What This Skill Does NOT Do
- Does not provide algorithmic tutorials or conceptual explanations (use
algo-annotation). - Does not generate skeletons or templates (use
solve-skeleton). - Does not create choice questions (use
choice-q-create, which reads mistake_log downstream).
2. Core Principle
Two parallel analysis paths that merge into a single comparison report:
+------------------------+
| User's solve() code |
+-----------+------------+
|
+-----------v------------+
| solve-analyze Skill |
+-----------+------------+
|
+---------------+----------------+
v v
Agent A: Static Analysis Agent B: Standard Solution
- Line-by-line logic review - Select template from
- Identify algorithm pattern solve-skeleton section 3
- Mark suspicious lines - Fill TODOs with correct logic
- Check anti-patterns from - Run anti-pattern checklist
solve-skeleton section 2 from solve-skeleton section 2
- Match known error patterns (references/exam-patterns.md,
from mistake_log.md references/algo-skeletons.md)
| |
+----------------+---------------+
v
Comparison Report
|
+----------------+----------------+
v v v
mistake_log user_profile experience MCP
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 455 lines · 160 tokens per session scan A 2226775d4f31
solve-analyze is a skill published in the GitHub repository Tenstu/Pass-LLM-with-LLM (5 stars, last pushed 2mo ago), licensed MIT. It adds 160 tokens to every session and 5,017 once invoked, about $0.0008 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
4-phase root cause debugging: understand bugs before fixing.
triage-issues
Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
sglang-diffusion-benchmark-profile
Use when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.