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 agentmods add skills/cocorof/geny-executor/debugnpx skills add CocoRoF/geny-executor --skill debuggit clone --depth 1 https://github.com/CocoRoF/geny-executorWhat 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 | $0.00034 | $0.00835 |
| Opus 5 | $0.00017 | $0.00417 |
| Sonnet 5 | $0.00007 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00084 |
Grade A, and why
Debug Snapshot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug — host + session diagnostic snapshot
The captured snapshot below is the ground truth. Read it carefully before suggesting any fix — many "obvious" fixes are wrong because the bug is one layer up (wrong PATH, wrong cwd, stale lock file, unset env var, dirty worktree).
Identity
- User: !
id -un - Groups: !
id -Gn - Hostname: !
hostname - Uptime: !
uptime
Filesystem context
- cwd: !
pwd - cwd writable?: !
[ -w "$(pwd)" ] && echo yes || echo no - Disk free (cwd): !
df -h "$(pwd)" 2>/dev/null | tail -n 1 || echo "(df failed)" - Inode pressure: !
df -i "$(pwd)" 2>/dev/null | tail -n 1 || echo "(df failed)"
Recently-touched files (last 5 minutes, current tree)
find . -maxdepth 3 -type f -mmin -5 -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/__pycache__/*" 2>/dev/null | head -n 20
Git activity (last 10 commits, current branch)
git log --oneline --decorate -n 10 2>/dev/null || echo "(not a git repo)"
Open ports / running listeners (TCP, IPv4)
{ ss -tln 2>/dev/null || netstat -tln 2>/dev/null || lsof -iTCP -sTCP:LISTEN -n 2>/dev/null; } | head -n 30
Resource snapshot
- Free memory: !
free -h 2>/dev/null | head -n 2 || echo "(free unavailable)" - Load average: !
cat /proc/loadavg 2>/dev/null || uptime | sed 's/.*load average: //' - Open file limit: !
ulimit -n
Selected env vars
env | grep -E '^(PATH|PYTHONPATH|NODE_ENV|VIRTUAL_ENV|HOME|USER|LANG|TZ|GENY_|ANTHROPIC_|OPENAI_)' | sed 's/=\(sk-\|ghp_\|gho_\)[A-Za-z0-9_-]*/=<redacted>/'
How to interpret
The data above is the input — your job is the output:
- Spot the anomaly. What's different from a clean dev box? Stale lock file? Stuck process on an unexpected port? cwd not writable? Dirty worktree masking a real fix?
- Tie it to the user's reported symptom. If they said "build fails", point at the disk-full / inode-exhausted / permission mismatch. If they said "tests hang", point at the listener / load / process state.
- Recommend at most one or two surgical fixes. Don't shotgun. Diagnostic skills earn trust by being precise.
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.
- yesterday First seen · 82 lines · 34 tokens per session scan A c907a10c41b9
Debug Snapshot is a skill published in the GitHub repository CocoRoF/geny-executor (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 835 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 2026-08-31.
Other skills, from other repositories
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.