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 ellmos-ai/skills --skill engit clone --depth 1 https://github.com/ellmos-ai/skillsWrote 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/ellmos-ai/skills/en)<a href="https://agentmods.dev/skills/ellmos-ai/skills/en"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/en/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/ellmos-ai/skills/en"><img src="https://agentmods.dev/badge/skills/ellmos-ai/skills/en.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 | $0.00034 | $0.02303 |
| Opus 5.5 | $0.00014 | $0.00921 |
| Sonnet 5.5 | $0.00007 | $0.00461 |
| Haiku 4.5 | $0.00003 | $0.00230 |
Grade C, and why
bugfix-protocol scanned grade C 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 26d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
find . -name "__pycache__" -type d -exec rm -rf {} + 2>&1 How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
English — Official English version of
bugfix-protocol.
Bugfix Protocol: Systematic 6-Phase Debugging
A structured approach to bugs — from symptom analysis to verification. Prevents aimless trial-and-error and ensures fixes are sustainable.
Overview & Purpose
| Phase | Name | Goal | Max. Time |
|---|---|---|---|
| 1 | Quick Checks | Rule out obvious causes | 2 min |
| 2 | Diagnosis | Locate root cause | 10 min |
| 3 | Isolated Test | Make bug reproducible | 5 min |
| 4 | Fix | Minimal correction | 10 min |
| 5 | Verification | Verify fix + check side effects | 5 min |
| 6 | Documentation | Preserve knowledge | 2 min |
20-Minute Rule: If no progress after 20 minutes, change approach or seek help.
Phase 1: Quick Checks (2 min)
Before diving deep — check the most common causes:
Checklist
- Syntax error? Read error message carefully, check line
- Import error? Module installed? Correct name? Circular import?
- Typo? Variable/function names correct?
- Wrong data type? String instead of int? None where object expected?
- Stale cache? Delete
__pycache__, restart - Wrong environment? Correct venv active? Correct Python version?
- Encoding? UTF-8 vs. cp1252 (Windows classic)
Quick Actions
# Clear cache
find . -name "__pycache__" -type d -exec rm -rf {} + 2>&1
find . -name "*.pyc" -delete 2>&1
# Check imports
python -c "import modulename"
# Check syntax
python -m py_compile file.py
Phase 2: Diagnosis (10 min)
Strategy: Outside-In
- Analyze error message — Read traceback from bottom to top
- Check recent changes —
git diff,git log --oneline -10 - Use diagnostic tools — Use project-specific diagnostic tools
Diagnostic Tools (Examples)
Depending on the project, specialized diagnostic scripts may be helpful:
| Tool | Purpose |
|---|---|
import_diagnose.py |
Analyze import problems |
method_analyzer.py |
Check method signatures |
env_checker.py |
Validate environment variables/paths |
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.
- 26d ago Changed 605b078ce654
- 1mo ago First seen · 334 lines · 34 tokens per session scan C 4e607ad53666
bugfix-protocol is a skill published in the GitHub repository ellmos-ai/skills (8 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 2,303 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
python-testing
Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization. Use when writing or improving Python tests.
diagnose
A disciplined workflow for investigating software that behaves incorrectly, crashes, produces wrong output, or fails intermittently. It first requires a repeatable command that can demonstrate the reported problem before testing possible causes.
python-rules
Python coding rules: style, patterns, security, testing. Triggers: .py, .pyi, pyproject.toml, requirements.txt, Pipfile, FastAPI, Django, Flask, pytest, SQLAlchemy, ruff, mypy.
python-idiomatic
Use when writing or reviewing Python language semantics, fixing aliasing, mutable defaults, late-bound closures, exhausted generators, import cycles, swallowed exceptions, or resource leaks; choosing comprehensions, decorators, context managers, match statements, or Python environment/debugging tools.
python-performance
Use when profiling, benchmarking, or optimizing Python CPU, memory, I/O, database, concurrency, startup, or numerical workloads; investigating leaks and performance regressions; reviewing optimization proposals; or validating before/after performance without changing behavior.
python-tdd
Use when implementing Python behavior test-first, reproducing bugs, characterizing legacy code, or applying red-green-refactor with pytest/unittest, fixtures, patch lookup, deterministic I/O and clocks, or Hypothesis properties. Covers coverage/mutation limits, not system-wide strategy or benchmarking.