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/everywan-dev/claude-code-engineering/check-if-data-is-safe-to-deletenpx skills add everywan-dev/claude-code-engineering --skill check-if-data-is-safe-to-deletegit clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringWrote 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/everywan-dev/claude-code-engineering/check-if-data-is-safe-to-delete)<a href="https://agentmods.dev/skills/everywan-dev/claude-code-engineering/check-if-data-is-safe-to-delete"><img src="https://agentmods.dev/badge/skills/everywan-dev/claude-code-engineering/check-if-data-is-safe-to-delete.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 5.1 | $0.00045 | $0.01448 |
| Opus 5 | $0.00023 | $0.00724 |
| Sonnet 5 | $0.00009 | $0.00290 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
check-if-data-is-safe-to-delete 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check if data is safe to delete
Something looks unused. A table nobody mentions, a file with an old timestamp, a service nobody remembers deploying. The question is whether it can go.
The answer is almost never obtainable by looking. It has to be measured, and the usual way of measuring it is wrong.
The rule
Absence of evidence is not evidence of absence. Every method below tells you "this thing is used". None of them tells you "this thing is unused" — they only fail to find a user, which is a different statement.
So the procedure is not "prove it is dead". It is: measure real access, then make deletion reversible, then wait, then delete.
What does not work
| Method | Why it fails |
|---|---|
| 🔴 Searching the codebase for the name | Access can be built at runtime, come from another repository, from a scheduled job, from a stored procedure, from a report tool, from a person with a client open |
| Last modified time | A read-heavy object is never modified. Old mtime is the normal state of something critical |
| "Nobody on the team knows what it is" | This describes the team's memory, not the system |
| Nothing broke in the test environment | The test environment is missing whichever caller is the dangerous one |
| A traffic graph that is flat | Check the window. Flat over 24 hours says nothing about a monthly job |
What does work
What the engine reports about actual access. Almost every system that stores things keeps its own access counters, and those counters see callers you cannot find any other way:
- A database engine → its per-table access statistics: scans, index lookups, rows fetched, last-accessed timestamp.
- A filesystem → access times, if
atimeis not disabled. Verify that it is not before trusting a reading. - A service → its own request log or metrics, and the connection table on the host.
Take the reading over a window long enough to include the slowest cycle you know about: nightly, weekly, monthly, and — for anything financial or regulatory — annual.
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 · 140 lines · 45 tokens per session scan A 2be4557defa4
check-if-data-is-safe-to-delete is a skill published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,448 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
claude-project-manifest
Creates annotated bibliography-style manifests for Claude projects, tracking files, conversation threads, and relationships with unique IDs and annotations. Use when documenting project contents, creating file inventories, tracking conversation history, or building navigable knowledge maps.
proofpress
Preserve or inspect decision history for Markdown and static HTML knowledge artifacts with Proofpress. Use when creating or accepting a meaningful revision to an ADR, design doc, PRD, README, strategy note, portable .md artifact, or static .html/.htm artifact in a configured repository, or when receiving a file…
book-to-skill
Use when convert technical books and documents (PDF, EPUB, DOCX, HTML, Markdown, RTF, MOBI) into structured agent skills with frameworks, mental models, chapter references, and decision rules. Includes full extraction pipeline. Use when the user wants to turn a book or document collection into a reusable agent skill…
proofpress-governed-context
Use Proofpress governed context when a task must rely on or hand off durable agent-produced knowledge, including evidence-backed decisions, experiment results, integration contracts, or incident learnings. Retrieve eligible context before relying on it; submit bounded proposals and receipts when a durable outcome is…
llm-wiki
Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.
Principle Synthesizer
Synthesize invariant principles from 3+ sources — find the core that survives across all expressions.