Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/BESSER-PEARL/BESSER-Skillsnpx agentmods add skills/besser-pearl/besser-skills/besser-troubleshootingWrote 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/besser-pearl/besser-skills/besser-troubleshooting)<a href="https://agentmods.dev/skills/besser-pearl/besser-skills/besser-troubleshooting"><img src="https://agentmods.dev/badge/skills/besser-pearl/besser-skills/besser-troubleshooting/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/besser-pearl/besser-skills/besser-troubleshooting"><img src="https://agentmods.dev/badge/skills/besser-pearl/besser-skills/besser-troubleshooting.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 | $0.00306 | $0.04176 |
| Opus 5.5 | $0.00122 | $0.01670 |
| Sonnet 5.5 | $0.00061 | $0.00835 |
| Haiku 4.5 | $0.00031 | $0.00418 |
Grade A, and why
besser-troubleshooting scanned grade A with 1 finding 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 2mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.CalledProcessError, or any other failure originating from How it starts
The opening of the file, as written. The whole thing — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BESSER Troubleshooting
Quick reference for diagnosing and fixing common issues. Organized by
symptom. This is an intentionally flat, single-file skill — a fast lookup
you scan top-to-bottom or search, with no references/ subdirectory.
Installation Issues
pip install besser fails with native dependency errors
Several BESSER dependencies require system libraries:
| Dependency | Requires | Fix (Ubuntu/Debian) | Fix (macOS) |
|---|---|---|---|
psycopg2-binary |
PostgreSQL client libs | apt install libpq-dev |
brew install postgresql |
pyodbc |
ODBC driver manager | apt install unixodbc-dev |
brew install unixodbc |
oracledb |
Oracle Instant Client | Download from Oracle | Download from Oracle |
If you don't need a specific database, these won't block core BESSER functionality — most generators work fine with SQLite (no native deps needed).
pip install -e . fails or installs nothing
- Must be run from the repository root (where
setup.cfgandpyproject.tomllive;setup.cfgholds the package metadata andpython_requires). - Requires
setuptools>=42andwheel. Upgrade first:pip install --upgrade setuptools wheel. - Check you're in the right virtual environment:
which python(Unix) orwhere python(Windows).
Python version incompatibility
BESSER requires Python 3.11+ (enforced by python_requires = >=3.11 in setup.cfg). Check with:
python --version
If you're on 3.10 or earlier, upgrade Python or use pyenv/conda to manage versions.
Windows-specific: venv\Scripts\activate not found
The activation path is venv\Scripts\activate (capital S). A common mistake in
some docs is venv\Script\activate (missing the 's') — this will fail.
:: Correct:
venv\Scripts\activate
Import Errors
ModuleNotFoundError: No module named 'besser'
- Not installed: Run
pip install -e .from the repo root, orpip install besser. - Wrong environment: Activate your venv first (
source venv/bin/activateorvenv\Scripts\activate). - Multiple Python installs:
pipandpythonmay point to different installations. Usepython -m pip install -e .to ensure alignment.
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.
- 2mo ago First seen · 419 lines · 306 tokens per session scan A 94d7fe7f6c03
besser-troubleshooting is a skill published in the GitHub repository BESSER-PEARL/BESSER-Skills (9 stars, last pushed 17d ago), licensed Apache-2.0. It adds 306 tokens to every session and 4,176 once invoked, about $0.0012 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
besser-troubleshooting compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| besser-troubleshootingBESSER-PEARL/BESSER-Skills | Skill | 9 | 17d ago | Apache-2.0 | A | 306 | Claude Code |
| systematic-debuggingNousResearch/hermes-agent | Skill | 261k | yesterday | MIT | A | 16 | Claude Code, Codex |
| cookie-debuggingasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 71 | Claude Code, Codex |
| a11y-debuggingasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 50 | Claude Code, Codex |
| observability-langsmithdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 44 | Claude Code, Codex |
| bug-reportDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 23 | Claude Code |
| bug-triageDonchitos/Claude-Code-Game-Studios | Skill | 36k | 19d ago | MIT | A | 30 | Claude Code |