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 commands/phoenix0531-sudo/tidy-skill/triggersgit clone --depth 1 https://github.com/Phoenix0531-sudo/tidy-skillWrote 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/commands/phoenix0531-sudo/tidy-skill/triggers)<a href="https://agentmods.dev/commands/phoenix0531-sudo/tidy-skill/triggers"><img src="https://agentmods.dev/badge/commands/phoenix0531-sudo/tidy-skill/triggers.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00694 |
| Opus 5 | $0.00000 | $0.00347 |
| Sonnet 5 | $0.00000 | $0.00139 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
TRIGGERS 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 5d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger phrases / slash-style commands
These are documentation triggers for hosts that map natural language or slash commands to skills. They do not install a runtime server.
Command stubs (markdown playbooks hosts can map):
- tidy.md — full read-only pass
- tidy-score.md — score only
- audit-artifacts.md — artifact scan
- tidy-doctor.md — install + hygiene doctor
- classify-path.md — pre-write class A–E check
| Trigger | Intent | Preferred tool |
|---|---|---|
/tidy or "run tidy-skill" |
Full local hygiene pass (read-only first) | score + artifact audit |
/tidy-score or "repo hygiene score" |
Score current repo 0-100 | score_repo_hygiene.py |
/tidy-doctor or "tidy doctor" |
Package + hygiene one-shot gate | tidy_doctor.py |
/classify-path or "should I create this file" |
Class A–E path check before write | classify_artifact.py |
/tidy-gate or "hygiene score gate" |
Fail CI if score below policy min | hygiene_snapshot.py gate |
/audit-artifacts or "scan agent files" |
List suspicious root process files | audit_agent_artifacts.py |
/audit-env or "why is my disk growing" |
Local cache / WSL / model footprint map | audit_dev_environment.py / .ps1 |
/audit-workspace |
Multi-repo parent folder audit | audit_workspace_hygiene.py |
/tidy-clean-preview |
DryRun cleanup preview only | clean-agent-artifacts.ps1 -DryRun |
/tidy-hooks-check |
End-of-task read-only stop check | hooks/stop-hygiene-check.py |
Canonical prompts
- "Score this repository's agent hygiene and list suspicious root Markdown."
- "Audit agent artifacts under the current repo; do not delete anything."
- "Map local package and model caches; separate safe suggestions from risky operations."
- "Scan every Git repo under
D:/Projectsfor plan.md/todo.md pollution." - "Preview cleanup of expired
.agent_tmpfiles in DryRun mode." - "Install tidy-skill into Claude and Codex skill folders (preview first)."
- "Install AGENTS.md hygiene rules into this project without overwriting unless forced."
- "Before you finish, run the read-only stop hygiene check."
- "Run tidy doctor on this repo and fail if score is below 80."
- "Classify whether
plan.mdat the root is allowed before creating it." - "Save a hygiene snapshot, then gate CI on
.tidy-skill.jsonmin_score."
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.
- 5d ago First seen · 45 lines · 0 tokens per session scan A ba4671e37a20
TRIGGERS is a command published in the GitHub repository Phoenix0531-sudo/tidy-skill (20 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 694 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 2026-08-30.
Other commands, from other repositories
profile
Save, apply, and share multi-agent configuration profiles.
doctor
Run a system health check to diagnose common issues.
init
Scaffold a new SKILL.md for your agent skill.
setup
One command. All agents. Skills + MCP servers. Zero configuration.
bundle
Install multiple skills at once from inline sources or a bundle file.
diff
Compare two SKILL.md files section-by-section. Parses frontmatter and body sections independently, showing exactly what changed.